SlideShare a Scribd company logo
1 of 46
Download to read offline
PRESENTERS: LI CHEN, RAVI SAHITA
CONTRIBUTORS: LI CHEN, RAVI SAHITA, CHIH-YUAN YANG, ANINDYA PAUL
Machine learning based
ransomware detection:
the good, the bad, and the ugly
Legal Disclaimers
• Intel provides these materials as-is, with no express or implied warranties.
• All products, dates, and figures specified are preliminary, based on current expectations, and are subject to change without notice.
• Intel processors, chipsets, and desktop boards may contain design defects or errors known as errata, which may cause the product to
deviate from published specifications. Current characterized errata are available on request.
• Intel technologies' features and benefits depend on system configuration and may require enabled hardware, software or service
activation. Performance varies depending on system configuration. No product or component can be absolutely secure. Check with
your system manufacturer or retailer or learn more at http://intel.com.
• Some results have been estimated or simulated using internal Intel analysis or architecture simulation or modeling, and provided to
you for informational purposes. Any differences in your system hardware, software or configuration may affect your actual
performance.
• Intel and the Intel logo are trademarks of Intel Corporation in the United States and other countries.
• *Other names and brands may be claimed as the property of others.
© Intel Corporation 2019
OUTLINE OF THE TALK
• Ransomware detection case study
• The Good:
• Machine Learning (ML) is effective
• The Bad:
• ML can launch adversarial attacks on ML models
• The Ugly:
• ML Model durability
• Improving detection via complementary platform capabilties
What is Ransomware?
• Ransomware is a category of malware which hijacks victim’s data or
machine and demands monetary returns
• Categories:
• Locker-ransomware: hijack resources without encryption
• Crypto-ransomware: deny access using encryption
• The damage done by crypto-ransomware is irreversible in most cases due
to the use of cryptography
Typical Ransomware ACTIVITY
Distribution Infection Communication
EnumerationEncryptionExtortion
Ransomware Data Description
• Downloaded total ~22k ransomware
using Microsoft and Kaspersky’s labels
from VirusTotal
• ~ 5min execution for each sample
• Decoy files to identify activated crypto-
ransomware - Identified ~4.4k active
samples
Ransomware families →
DATA ACQUISITION VIA Sandbox
System
• Bare-metal system built on
Windows*-based system
• Refresh system by checkpointing
SSD writes and restoring SSD
partition image
• Anti-evasion mechanisms
• Simulated human activities
• Opened applications
• Limited heuristics
Storage
Control
Server
Storage
Robot
Internet
Data
storage
Router
Programmable
Power Control
…
Robot
Behavior Data BASED ON I/O Events
• Collected Time stamp, I/O Event Type, Target Filename, Entropy
• Based on C# .Net framework FileSystemWatcher
• Entropy of target files calculated by normalized Shannon entropy
The Good
Machine learning can be
efficient, scalable and
accurate at recognizing
malicious attacks.
Feature extraction
Events Feature
encoding
Padding 0
File deleted 1
File content changed and entropy is [0.9, 1] 2
File content changed and entropy is [0.2, 0.4) 3
File content changed and entropy is [0, 0.2) 4
File created 5
File content changed and entropy is [0.8, 0.9) 6
File renamed 7
File content changed and entropy is [0.4, 0.6) 8
File content changed and entropy is [0.6, 0.8) 9
• Each execution log is
represented by a
sequence of events.
• We set the length = 3000
for each sample.
ML model results for ransomware
detection
❖Train-Test ratio: 0.8:0.2
❖Training samples: 1292 benign, 3736 malicious
❖Test samples: 324 benign, 934 malicious
❖Dimensionality: n x 3000
❖7 ML models
We select Text CNN as feature
extractor due to its superior
performance compared with
other classifiers.
text-cnn feature space
https://arxiv.org/pdf/1408.5882v2.pdf
Feature
subspace
Features are well-separated in Text-
CNN subspace
Class-conditional density plot for each dimension in Text-CNN feature space.
classifiers greatly improve in Text CNN
feature subspace
Classifiers improve up to 55% in accuracy in Text-CNN space.
The Good - summary
Machine learning is highly effective for malware detection.
When ML classifiers are used in security-critical applications,
are accuracy, FPR, precision, recall, F1 scores enough?
The Bad
Machine learning can hack
vulnerable ML systems.
Adversarial Machine Learning in Vision
Object Detection
(amplified)
DNN: “Speed Limit Sign” DNN: “Ruler”Difference
Image Classification
https://arxiv.org/abs/1412.6572
https://arxiv.org/abs/1703.08603
Adversarial Pertubation
Object detection on original image with
adversarial pertubationObject detection on original image
Generative Adversarial Network
(GAN)
Generator
Discriminator
G generates fakes to fool D
D differentiates fakes and reals.
Over time, G and D get better.
Goodfellow, Ian, et al. "Generative adversarial nets." Advances in neural information processing systems. 2014.
Core Idea: GAN to synthesize
ransomware logs
Our threat model assumes the adversary has access to training dataset but has no
knowledge of the ML classifier.
adversarial quality assessment
A successful evasion means the generated malicious samples not
only fool ransomware classifier, but also persists maliciousness
based on certain metrics.
We propose sample-based and batch-based adversarial quality
metrics to evaluate
Overview of Methodology
GAN to bypass ransomware detection
• We use the same training data to train AC-GAN
• The stopping criterion is based on the loss of the
discriminator
• At test time, we generate 5000 malicious segments and
ensure their adversarial quality
Detection results on good quality
adversarial examples
Indicates a broad attack surface for ML
THE BAD - SUMMARY
Machine learning can automatically hack other highly effective
ML systems. Generative adversarial network can serve as an
intelligent hacker to bypass effective systems.
Robustness and resiliency are equally important as accuracy,
FPR, precision, recall, F1 scores.
Why does this happen?
The Ugly
The investigation
Concept drift
Time variant samples
Investigation
We investigate why the
generated samples can
bypass ML detection
The generated samples, in
dark red, lie close to a
linear boundary but much
closer to the real benign
samples in the Text-CNN
latent feature subspace
Non-linear boundary decision shows to
be more robust
• SVM with radial basis in
Text-CNN space was able
to detect all the
adversarial examples
• The non-linear boundary
decision pertain
robustness and indicates
a smaller blindspot
Other issues
• Concept drift
• Time variant
The Ugly - summary:
Investigation of ML boundaries indicates adversarial
samples lie close to the benign samples in feature
subspace.
Nonlinear boundary decisions show better resiliency
against adversarial examples.
Platform
capabilities
to improve
detection
Making the attackers job
harder
Intel Labs
Analytical to real-world samples
How to take the output of GAN and incorporate it in the tool to
run ransomware?
PLATFORM capabilities to make ML system
more trustworthy
• Can we use ML + system capabilities to make the attackers’ job harder?
• Intel® Processor Trace and other telemetry can be used to make the system call
activity information more trustworthy
• Checkpointing technologies are a useful tool for recovery
• Trusted Execution capabilities can prevent model stealing attacks
• New storage mechanisms (such as persistent memory) provide new avenues for
access-control
Backup
Ransomware Mitigation
Ransomware
ML DetectorRollback
File IO Events, Entropy, Path
Early Detection
USE ML AS AN EARLY DETECTOR
ML VULNERABILITY RESEARCH PLATFORM
- MLsploit
• A Cloud-Based Framework for Adversarial
Machine Learning Research
• Tool for interactive investigation of ML
vulnerabilities
• Interactive interface and iterative
experimentation
• Comparison for attack and defenses
SUMMARY
• ML can be used to build efficient, scalable and accurate at recognizing malicious
attacks such as ransomware
• ML can also be used to hack vulnerable ML systems
• ML models must comprehend adversarial approaches, concept drift and time
variations
• Combing platform capabilities for attack surface reduction (prevention) and
recovery capabilities can complement ML detection for robust solutions
BACKUP MATERIAL
Training AC-GAN
39
The intersection of AI & Security
40
Security Analytics Secure AI Workloads Adversarial Resilient AI
Today’s focus
Case Study
• Collect real ransomware and benign software
• Examine ML effectiveness for ransomware detection
• Explore ML robustness when ML generates adversarial ransomware
samples
• Investigate ML blind spot and boundaries
classifiers greatly improve in Text CNN
feature subspace
43
Beyond vision: audio or malware
Attack in ASR domain on audio waveforms to fool
DeepSpeech (speech-to-text transcription)
AVPASS: adversarial malwares variants that can
beat VirusTotal detection
https://arxiv.org/abs/1801.01944
https://www.blackhat.com/us-17/briefings/schedule/#avpass-leaking-and-bypassing-antivirus-detection-model-automatically-7354
Bypass VirusTotal
up to 100%
Training GAN
Challenges:
❖Convergence issue:
❖Transfer learning
❖Learning rates adapted for generator and discriminaro
• We use the same training data to train AC-GAN
• The stopping criterion is based on the loss of the discriminator
• At test time, we generate 5000 malicious segments
44
adversarial quality metric
Batch-basedSample-based
Indicates the generated samples are much more alike malicious real ransomware samples
Distribution difference in original and
feature space

More Related Content

What's hot

Design and Development of an Efficient Malware Detection Using ML
Design and Development of an Efficient Malware Detection Using MLDesign and Development of an Efficient Malware Detection Using ML
Design and Development of an Efficient Malware Detection Using MLSiva krishnam raju Patsamatla
 
Penetration testing overview
Penetration testing overviewPenetration testing overview
Penetration testing overviewSupriya G
 
Penentration testing
Penentration testingPenentration testing
Penentration testingtahreemsaleem
 
Automating networksecurityassessment
Automating networksecurityassessmentAutomating networksecurityassessment
Automating networksecurityassessmentGlib Pakharenko
 
Defending deep learning from adversarial attacks
Defending deep learning from adversarial attacksDefending deep learning from adversarial attacks
Defending deep learning from adversarial attacksSvetlana Levitan, PhD
 
Applying Provenance in APT Monitoring and Analysis Practical Challenges for S...
Applying Provenance in APT Monitoring and Analysis Practical Challenges for S...Applying Provenance in APT Monitoring and Analysis Practical Challenges for S...
Applying Provenance in APT Monitoring and Analysis Practical Challenges for S...Graeme Jenkinson
 
Permutation Oriented Programming
Permutation Oriented ProgrammingPermutation Oriented Programming
Permutation Oriented ProgrammingNelson Brito
 
Proposal defense presentation
Proposal defense presentationProposal defense presentation
Proposal defense presentationRuchika Mehresh
 
SmartphoneHacking_Android_Exploitation
SmartphoneHacking_Android_ExploitationSmartphoneHacking_Android_Exploitation
SmartphoneHacking_Android_ExploitationMalachi Jones
 
Infiltrate 2015 - Data Driven Offense
Infiltrate 2015 - Data Driven Offense Infiltrate 2015 - Data Driven Offense
Infiltrate 2015 - Data Driven Offense Ram Shankar Siva Kumar
 
A malware detection method for health sensor data based on machine learning
A malware detection method for health sensor data based on machine learningA malware detection method for health sensor data based on machine learning
A malware detection method for health sensor data based on machine learningjaigera
 
Webinar on Functional Safety Analysis using Model-based System Analysis
Webinar on Functional Safety Analysis using Model-based System AnalysisWebinar on Functional Safety Analysis using Model-based System Analysis
Webinar on Functional Safety Analysis using Model-based System AnalysisDeepak Shankar
 
Vulnerability assessment and penetration testing
Vulnerability assessment and penetration testingVulnerability assessment and penetration testing
Vulnerability assessment and penetration testingAbu Sadat Mohammed Yasin
 
Stuxnet redux. malware attribution & lessons learned
Stuxnet redux. malware attribution & lessons learnedStuxnet redux. malware attribution & lessons learned
Stuxnet redux. malware attribution & lessons learnedYury Chemerkin
 
Introduction of Threat Analysis Methods(FFRI Monthly Research 2016.9)
Introduction of Threat Analysis Methods(FFRI Monthly Research 2016.9)Introduction of Threat Analysis Methods(FFRI Monthly Research 2016.9)
Introduction of Threat Analysis Methods(FFRI Monthly Research 2016.9)FFRI, Inc.
 
TriggerScope: Towards Detecting Logic Bombs in Android Applications
TriggerScope: Towards Detecting Logic Bombs in Android ApplicationsTriggerScope: Towards Detecting Logic Bombs in Android Applications
TriggerScope: Towards Detecting Logic Bombs in Android ApplicationsPietro De Nicolao
 
COMPARISON OF MALWARE CLASSIFICATION METHODS USING CONVOLUTIONAL NEURAL NETWO...
COMPARISON OF MALWARE CLASSIFICATION METHODS USING CONVOLUTIONAL NEURAL NETWO...COMPARISON OF MALWARE CLASSIFICATION METHODS USING CONVOLUTIONAL NEURAL NETWO...
COMPARISON OF MALWARE CLASSIFICATION METHODS USING CONVOLUTIONAL NEURAL NETWO...IJNSA Journal
 
Adversarial robustness using clever hans
Adversarial robustness using clever hansAdversarial robustness using clever hans
Adversarial robustness using clever hansShrutiMishra164
 
AI approach to malware similarity analysis: Maping the malware genome with a...
AI approach to malware similarity analysis: Maping the  malware genome with a...AI approach to malware similarity analysis: Maping the  malware genome with a...
AI approach to malware similarity analysis: Maping the malware genome with a...Priyanka Aash
 
STRIDE Variants and Security Requirements-based Threat Analysis (FFRI Monthly...
STRIDE Variants and Security Requirements-based Threat Analysis (FFRI Monthly...STRIDE Variants and Security Requirements-based Threat Analysis (FFRI Monthly...
STRIDE Variants and Security Requirements-based Threat Analysis (FFRI Monthly...FFRI, Inc.
 

What's hot (20)

Design and Development of an Efficient Malware Detection Using ML
Design and Development of an Efficient Malware Detection Using MLDesign and Development of an Efficient Malware Detection Using ML
Design and Development of an Efficient Malware Detection Using ML
 
Penetration testing overview
Penetration testing overviewPenetration testing overview
Penetration testing overview
 
Penentration testing
Penentration testingPenentration testing
Penentration testing
 
Automating networksecurityassessment
Automating networksecurityassessmentAutomating networksecurityassessment
Automating networksecurityassessment
 
Defending deep learning from adversarial attacks
Defending deep learning from adversarial attacksDefending deep learning from adversarial attacks
Defending deep learning from adversarial attacks
 
Applying Provenance in APT Monitoring and Analysis Practical Challenges for S...
Applying Provenance in APT Monitoring and Analysis Practical Challenges for S...Applying Provenance in APT Monitoring and Analysis Practical Challenges for S...
Applying Provenance in APT Monitoring and Analysis Practical Challenges for S...
 
Permutation Oriented Programming
Permutation Oriented ProgrammingPermutation Oriented Programming
Permutation Oriented Programming
 
Proposal defense presentation
Proposal defense presentationProposal defense presentation
Proposal defense presentation
 
SmartphoneHacking_Android_Exploitation
SmartphoneHacking_Android_ExploitationSmartphoneHacking_Android_Exploitation
SmartphoneHacking_Android_Exploitation
 
Infiltrate 2015 - Data Driven Offense
Infiltrate 2015 - Data Driven Offense Infiltrate 2015 - Data Driven Offense
Infiltrate 2015 - Data Driven Offense
 
A malware detection method for health sensor data based on machine learning
A malware detection method for health sensor data based on machine learningA malware detection method for health sensor data based on machine learning
A malware detection method for health sensor data based on machine learning
 
Webinar on Functional Safety Analysis using Model-based System Analysis
Webinar on Functional Safety Analysis using Model-based System AnalysisWebinar on Functional Safety Analysis using Model-based System Analysis
Webinar on Functional Safety Analysis using Model-based System Analysis
 
Vulnerability assessment and penetration testing
Vulnerability assessment and penetration testingVulnerability assessment and penetration testing
Vulnerability assessment and penetration testing
 
Stuxnet redux. malware attribution & lessons learned
Stuxnet redux. malware attribution & lessons learnedStuxnet redux. malware attribution & lessons learned
Stuxnet redux. malware attribution & lessons learned
 
Introduction of Threat Analysis Methods(FFRI Monthly Research 2016.9)
Introduction of Threat Analysis Methods(FFRI Monthly Research 2016.9)Introduction of Threat Analysis Methods(FFRI Monthly Research 2016.9)
Introduction of Threat Analysis Methods(FFRI Monthly Research 2016.9)
 
TriggerScope: Towards Detecting Logic Bombs in Android Applications
TriggerScope: Towards Detecting Logic Bombs in Android ApplicationsTriggerScope: Towards Detecting Logic Bombs in Android Applications
TriggerScope: Towards Detecting Logic Bombs in Android Applications
 
COMPARISON OF MALWARE CLASSIFICATION METHODS USING CONVOLUTIONAL NEURAL NETWO...
COMPARISON OF MALWARE CLASSIFICATION METHODS USING CONVOLUTIONAL NEURAL NETWO...COMPARISON OF MALWARE CLASSIFICATION METHODS USING CONVOLUTIONAL NEURAL NETWO...
COMPARISON OF MALWARE CLASSIFICATION METHODS USING CONVOLUTIONAL NEURAL NETWO...
 
Adversarial robustness using clever hans
Adversarial robustness using clever hansAdversarial robustness using clever hans
Adversarial robustness using clever hans
 
AI approach to malware similarity analysis: Maping the malware genome with a...
AI approach to malware similarity analysis: Maping the  malware genome with a...AI approach to malware similarity analysis: Maping the  malware genome with a...
AI approach to malware similarity analysis: Maping the malware genome with a...
 
STRIDE Variants and Security Requirements-based Threat Analysis (FFRI Monthly...
STRIDE Variants and Security Requirements-based Threat Analysis (FFRI Monthly...STRIDE Variants and Security Requirements-based Threat Analysis (FFRI Monthly...
STRIDE Variants and Security Requirements-based Threat Analysis (FFRI Monthly...
 

Similar to BlueHat Seattle 2019 || The good, the bad & the ugly of ML based approaches for ransomware detection

BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6Rod Soto
 
Cybersecurity Challenges with Generative AI - for Good and Bad
Cybersecurity Challenges with Generative AI - for Good and BadCybersecurity Challenges with Generative AI - for Good and Bad
Cybersecurity Challenges with Generative AI - for Good and BadIvo Andreev
 
Network security monitoring elastic webinar - 16 june 2021
Network security monitoring   elastic webinar - 16 june 2021Network security monitoring   elastic webinar - 16 june 2021
Network security monitoring elastic webinar - 16 june 2021Mouaz Alnouri
 
Subverting Machine Learning Detections for fun and profit
Subverting Machine Learning Detections for fun and profitSubverting Machine Learning Detections for fun and profit
Subverting Machine Learning Detections for fun and profitRam Shankar Siva Kumar
 
AI for Cybersecurity Innovation
AI for Cybersecurity InnovationAI for Cybersecurity Innovation
AI for Cybersecurity InnovationPete Burnap
 
Icacci presentation-isi-ransomware
Icacci presentation-isi-ransomwareIcacci presentation-isi-ransomware
Icacci presentation-isi-ransomwarevinaykumar R
 
Machine learning in Cyber Security
Machine learning in Cyber SecurityMachine learning in Cyber Security
Machine learning in Cyber SecurityRajathV2
 
TakeDownCon Rocket City: Research Advancements Towards Protecting Critical As...
TakeDownCon Rocket City: Research Advancements Towards Protecting Critical As...TakeDownCon Rocket City: Research Advancements Towards Protecting Critical As...
TakeDownCon Rocket City: Research Advancements Towards Protecting Critical As...EC-Council
 
malware detection ppt for vtu project and other final year project
malware detection ppt for vtu project and other final year projectmalware detection ppt for vtu project and other final year project
malware detection ppt for vtu project and other final year projectNaveenAd4
 
Navy security contest-bigdataforsecurity
Navy security contest-bigdataforsecurityNavy security contest-bigdataforsecurity
Navy security contest-bigdataforsecuritystelligence
 
Machine Learning for Malware Classification and Clustering
Machine Learning for Malware Classification and ClusteringMachine Learning for Malware Classification and Clustering
Machine Learning for Malware Classification and ClusteringAshwini Almad
 
Machine Learning for Malware Classification and Clustering
Machine Learning for Malware Classification and ClusteringMachine Learning for Malware Classification and Clustering
Machine Learning for Malware Classification and ClusteringEndgameInc
 
Malware Collection and Analysis via Hardware Virtualization
Malware Collection and Analysis via Hardware VirtualizationMalware Collection and Analysis via Hardware Virtualization
Malware Collection and Analysis via Hardware VirtualizationTamas K Lengyel
 
chap-1 : Vulnerabilities in Information Systems
chap-1 : Vulnerabilities in Information Systemschap-1 : Vulnerabilities in Information Systems
chap-1 : Vulnerabilities in Information SystemsKashfUlHuda1
 
Is av dead or just missing in action - avar2016
Is av dead or just missing in action - avar2016Is av dead or just missing in action - avar2016
Is av dead or just missing in action - avar2016rajeshnikam
 
Machine Learning AND Deep Learning for OpenPOWER
Machine Learning AND Deep Learning for OpenPOWERMachine Learning AND Deep Learning for OpenPOWER
Machine Learning AND Deep Learning for OpenPOWERGanesan Narayanasamy
 
DEF CON 27 - CHRISTOPHER ROBERTS - firmware slap
DEF CON 27 - CHRISTOPHER ROBERTS - firmware slapDEF CON 27 - CHRISTOPHER ROBERTS - firmware slap
DEF CON 27 - CHRISTOPHER ROBERTS - firmware slapFelipe Prado
 

Similar to BlueHat Seattle 2019 || The good, the bad & the ugly of ML based approaches for ransomware detection (20)

BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6
 
Cybersecurity Challenges with Generative AI - for Good and Bad
Cybersecurity Challenges with Generative AI - for Good and BadCybersecurity Challenges with Generative AI - for Good and Bad
Cybersecurity Challenges with Generative AI - for Good and Bad
 
Network security monitoring elastic webinar - 16 june 2021
Network security monitoring   elastic webinar - 16 june 2021Network security monitoring   elastic webinar - 16 june 2021
Network security monitoring elastic webinar - 16 june 2021
 
Subverting Machine Learning Detections for fun and profit
Subverting Machine Learning Detections for fun and profitSubverting Machine Learning Detections for fun and profit
Subverting Machine Learning Detections for fun and profit
 
AI for Cybersecurity Innovation
AI for Cybersecurity InnovationAI for Cybersecurity Innovation
AI for Cybersecurity Innovation
 
Icacci presentation-isi-ransomware
Icacci presentation-isi-ransomwareIcacci presentation-isi-ransomware
Icacci presentation-isi-ransomware
 
Machine learning in Cyber Security
Machine learning in Cyber SecurityMachine learning in Cyber Security
Machine learning in Cyber Security
 
TakeDownCon Rocket City: Research Advancements Towards Protecting Critical As...
TakeDownCon Rocket City: Research Advancements Towards Protecting Critical As...TakeDownCon Rocket City: Research Advancements Towards Protecting Critical As...
TakeDownCon Rocket City: Research Advancements Towards Protecting Critical As...
 
malware detection ppt for vtu project and other final year project
malware detection ppt for vtu project and other final year projectmalware detection ppt for vtu project and other final year project
malware detection ppt for vtu project and other final year project
 
Navy security contest-bigdataforsecurity
Navy security contest-bigdataforsecurityNavy security contest-bigdataforsecurity
Navy security contest-bigdataforsecurity
 
Machine Learning for Malware Classification and Clustering
Machine Learning for Malware Classification and ClusteringMachine Learning for Malware Classification and Clustering
Machine Learning for Malware Classification and Clustering
 
Machine Learning for Malware Classification and Clustering
Machine Learning for Malware Classification and ClusteringMachine Learning for Malware Classification and Clustering
Machine Learning for Malware Classification and Clustering
 
Talos
TalosTalos
Talos
 
Malware Collection and Analysis via Hardware Virtualization
Malware Collection and Analysis via Hardware VirtualizationMalware Collection and Analysis via Hardware Virtualization
Malware Collection and Analysis via Hardware Virtualization
 
chap-1 : Vulnerabilities in Information Systems
chap-1 : Vulnerabilities in Information Systemschap-1 : Vulnerabilities in Information Systems
chap-1 : Vulnerabilities in Information Systems
 
Is av dead or just missing in action - avar2016
Is av dead or just missing in action - avar2016Is av dead or just missing in action - avar2016
Is av dead or just missing in action - avar2016
 
Is Antivirus (AV) Dead or Just Missing in Action
Is Antivirus (AV) Dead or Just Missing in Action Is Antivirus (AV) Dead or Just Missing in Action
Is Antivirus (AV) Dead or Just Missing in Action
 
Machine Learning AND Deep Learning for OpenPOWER
Machine Learning AND Deep Learning for OpenPOWERMachine Learning AND Deep Learning for OpenPOWER
Machine Learning AND Deep Learning for OpenPOWER
 
Foutse_Khomh.pptx
Foutse_Khomh.pptxFoutse_Khomh.pptx
Foutse_Khomh.pptx
 
DEF CON 27 - CHRISTOPHER ROBERTS - firmware slap
DEF CON 27 - CHRISTOPHER ROBERTS - firmware slapDEF CON 27 - CHRISTOPHER ROBERTS - firmware slap
DEF CON 27 - CHRISTOPHER ROBERTS - firmware slap
 

More from BlueHat Security Conference

BlueHat Seattle 2019 || The cake is a lie! Uncovering the secret world of mal...
BlueHat Seattle 2019 || The cake is a lie! Uncovering the secret world of mal...BlueHat Seattle 2019 || The cake is a lie! Uncovering the secret world of mal...
BlueHat Seattle 2019 || The cake is a lie! Uncovering the secret world of mal...BlueHat Security Conference
 
BlueHat Seattle 2019 || Guarding Against Physical Attacks: The Xbox One Story
BlueHat Seattle 2019 || Guarding Against Physical Attacks: The Xbox One StoryBlueHat Seattle 2019 || Guarding Against Physical Attacks: The Xbox One Story
BlueHat Seattle 2019 || Guarding Against Physical Attacks: The Xbox One StoryBlueHat Security Conference
 
BlueHat Seattle 2019 || Kubernetes Practical Attack and Defense
BlueHat Seattle 2019 || Kubernetes Practical Attack and DefenseBlueHat Seattle 2019 || Kubernetes Practical Attack and Defense
BlueHat Seattle 2019 || Kubernetes Practical Attack and DefenseBlueHat Security Conference
 
BlueHat Seattle 2019 || Open Source Security, vulnerabilities never come alone
BlueHat Seattle 2019 || Open Source Security, vulnerabilities never come aloneBlueHat Seattle 2019 || Open Source Security, vulnerabilities never come alone
BlueHat Seattle 2019 || Open Source Security, vulnerabilities never come aloneBlueHat Security Conference
 
BlueHat Seattle 2019 || Modern Binary Analysis with ILs
BlueHat Seattle 2019 || Modern Binary Analysis with ILsBlueHat Seattle 2019 || Modern Binary Analysis with ILs
BlueHat Seattle 2019 || Modern Binary Analysis with ILsBlueHat Security Conference
 
BlueHat Seattle 2019 || Don't forget to SUBSCRIBE.
BlueHat Seattle 2019 || Don't forget to SUBSCRIBE.BlueHat Seattle 2019 || Don't forget to SUBSCRIBE.
BlueHat Seattle 2019 || Don't forget to SUBSCRIBE.BlueHat Security Conference
 
BlueHat Seattle 2019 || I'm in your cloud: A year of hacking Azure AD
BlueHat Seattle 2019 || I'm in your cloud: A year of hacking Azure ADBlueHat Seattle 2019 || I'm in your cloud: A year of hacking Azure AD
BlueHat Seattle 2019 || I'm in your cloud: A year of hacking Azure ADBlueHat Security Conference
 
BlueHat Seattle 2019 || Autopsies of Recent DFIR Investigations
BlueHat Seattle 2019 || Autopsies of Recent DFIR InvestigationsBlueHat Seattle 2019 || Autopsies of Recent DFIR Investigations
BlueHat Seattle 2019 || Autopsies of Recent DFIR InvestigationsBlueHat Security Conference
 
BlueHat Seattle 2019 || Are We There Yet: Why Does Application Security Take ...
BlueHat Seattle 2019 || Are We There Yet: Why Does Application Security Take ...BlueHat Seattle 2019 || Are We There Yet: Why Does Application Security Take ...
BlueHat Seattle 2019 || Are We There Yet: Why Does Application Security Take ...BlueHat Security Conference
 
BlueHat Seattle 2019 || Building Secure Machine Learning Pipelines: Security ...
BlueHat Seattle 2019 || Building Secure Machine Learning Pipelines: Security ...BlueHat Seattle 2019 || Building Secure Machine Learning Pipelines: Security ...
BlueHat Seattle 2019 || Building Secure Machine Learning Pipelines: Security ...BlueHat Security Conference
 
BlueHat v18 || First strontium uefi rootkit unveiled
BlueHat v18 || First strontium uefi rootkit unveiledBlueHat v18 || First strontium uefi rootkit unveiled
BlueHat v18 || First strontium uefi rootkit unveiledBlueHat Security Conference
 
BlueHat v18 || WSL reloaded - Let's try to do better fuzzing
BlueHat v18 || WSL reloaded - Let's try to do better fuzzingBlueHat v18 || WSL reloaded - Let's try to do better fuzzing
BlueHat v18 || WSL reloaded - Let's try to do better fuzzingBlueHat Security Conference
 
BlueHat v18 || The hitchhiker's guide to north korea's malware galaxy
BlueHat v18 || The hitchhiker's guide to north korea's malware galaxyBlueHat v18 || The hitchhiker's guide to north korea's malware galaxy
BlueHat v18 || The hitchhiker's guide to north korea's malware galaxyBlueHat Security Conference
 
BlueHat v18 || Retpoline - the anti-spectre (type 2) mitigation in windows
BlueHat v18 || Retpoline - the anti-spectre (type 2) mitigation in windowsBlueHat v18 || Retpoline - the anti-spectre (type 2) mitigation in windows
BlueHat v18 || Retpoline - the anti-spectre (type 2) mitigation in windowsBlueHat Security Conference
 
BlueHat v18 || Memory resident implants - code injection is alive and well
BlueHat v18 || Memory resident implants - code injection is alive and wellBlueHat v18 || Memory resident implants - code injection is alive and well
BlueHat v18 || Memory resident implants - code injection is alive and wellBlueHat Security Conference
 
BlueHat v18 || Massive scale usb device driver fuzz without device
BlueHat v18 || Massive scale usb device driver fuzz without deviceBlueHat v18 || Massive scale usb device driver fuzz without device
BlueHat v18 || Massive scale usb device driver fuzz without deviceBlueHat Security Conference
 
BlueHat v18 || Modern day entomology - examining the inner workings of the bu...
BlueHat v18 || Modern day entomology - examining the inner workings of the bu...BlueHat v18 || Modern day entomology - examining the inner workings of the bu...
BlueHat v18 || Modern day entomology - examining the inner workings of the bu...BlueHat Security Conference
 
BlueHat v18 || The matrix has you - protecting linux using deception
BlueHat v18 || The matrix has you - protecting linux using deceptionBlueHat v18 || The matrix has you - protecting linux using deception
BlueHat v18 || The matrix has you - protecting linux using deceptionBlueHat Security Conference
 
BlueHat v18 || An ice-cold boot to break bit locker
BlueHat v18 || An ice-cold boot to break bit lockerBlueHat v18 || An ice-cold boot to break bit locker
BlueHat v18 || An ice-cold boot to break bit lockerBlueHat Security Conference
 

More from BlueHat Security Conference (20)

BlueHat Seattle 2019 || The cake is a lie! Uncovering the secret world of mal...
BlueHat Seattle 2019 || The cake is a lie! Uncovering the secret world of mal...BlueHat Seattle 2019 || The cake is a lie! Uncovering the secret world of mal...
BlueHat Seattle 2019 || The cake is a lie! Uncovering the secret world of mal...
 
BlueHat Seattle 2019 || Keynote
BlueHat Seattle 2019 || KeynoteBlueHat Seattle 2019 || Keynote
BlueHat Seattle 2019 || Keynote
 
BlueHat Seattle 2019 || Guarding Against Physical Attacks: The Xbox One Story
BlueHat Seattle 2019 || Guarding Against Physical Attacks: The Xbox One StoryBlueHat Seattle 2019 || Guarding Against Physical Attacks: The Xbox One Story
BlueHat Seattle 2019 || Guarding Against Physical Attacks: The Xbox One Story
 
BlueHat Seattle 2019 || Kubernetes Practical Attack and Defense
BlueHat Seattle 2019 || Kubernetes Practical Attack and DefenseBlueHat Seattle 2019 || Kubernetes Practical Attack and Defense
BlueHat Seattle 2019 || Kubernetes Practical Attack and Defense
 
BlueHat Seattle 2019 || Open Source Security, vulnerabilities never come alone
BlueHat Seattle 2019 || Open Source Security, vulnerabilities never come aloneBlueHat Seattle 2019 || Open Source Security, vulnerabilities never come alone
BlueHat Seattle 2019 || Open Source Security, vulnerabilities never come alone
 
BlueHat Seattle 2019 || Modern Binary Analysis with ILs
BlueHat Seattle 2019 || Modern Binary Analysis with ILsBlueHat Seattle 2019 || Modern Binary Analysis with ILs
BlueHat Seattle 2019 || Modern Binary Analysis with ILs
 
BlueHat Seattle 2019 || Don't forget to SUBSCRIBE.
BlueHat Seattle 2019 || Don't forget to SUBSCRIBE.BlueHat Seattle 2019 || Don't forget to SUBSCRIBE.
BlueHat Seattle 2019 || Don't forget to SUBSCRIBE.
 
BlueHat Seattle 2019 || I'm in your cloud: A year of hacking Azure AD
BlueHat Seattle 2019 || I'm in your cloud: A year of hacking Azure ADBlueHat Seattle 2019 || I'm in your cloud: A year of hacking Azure AD
BlueHat Seattle 2019 || I'm in your cloud: A year of hacking Azure AD
 
BlueHat Seattle 2019 || Autopsies of Recent DFIR Investigations
BlueHat Seattle 2019 || Autopsies of Recent DFIR InvestigationsBlueHat Seattle 2019 || Autopsies of Recent DFIR Investigations
BlueHat Seattle 2019 || Autopsies of Recent DFIR Investigations
 
BlueHat Seattle 2019 || Are We There Yet: Why Does Application Security Take ...
BlueHat Seattle 2019 || Are We There Yet: Why Does Application Security Take ...BlueHat Seattle 2019 || Are We There Yet: Why Does Application Security Take ...
BlueHat Seattle 2019 || Are We There Yet: Why Does Application Security Take ...
 
BlueHat Seattle 2019 || Building Secure Machine Learning Pipelines: Security ...
BlueHat Seattle 2019 || Building Secure Machine Learning Pipelines: Security ...BlueHat Seattle 2019 || Building Secure Machine Learning Pipelines: Security ...
BlueHat Seattle 2019 || Building Secure Machine Learning Pipelines: Security ...
 
BlueHat v18 || First strontium uefi rootkit unveiled
BlueHat v18 || First strontium uefi rootkit unveiledBlueHat v18 || First strontium uefi rootkit unveiled
BlueHat v18 || First strontium uefi rootkit unveiled
 
BlueHat v18 || WSL reloaded - Let's try to do better fuzzing
BlueHat v18 || WSL reloaded - Let's try to do better fuzzingBlueHat v18 || WSL reloaded - Let's try to do better fuzzing
BlueHat v18 || WSL reloaded - Let's try to do better fuzzing
 
BlueHat v18 || The hitchhiker's guide to north korea's malware galaxy
BlueHat v18 || The hitchhiker's guide to north korea's malware galaxyBlueHat v18 || The hitchhiker's guide to north korea's malware galaxy
BlueHat v18 || The hitchhiker's guide to north korea's malware galaxy
 
BlueHat v18 || Retpoline - the anti-spectre (type 2) mitigation in windows
BlueHat v18 || Retpoline - the anti-spectre (type 2) mitigation in windowsBlueHat v18 || Retpoline - the anti-spectre (type 2) mitigation in windows
BlueHat v18 || Retpoline - the anti-spectre (type 2) mitigation in windows
 
BlueHat v18 || Memory resident implants - code injection is alive and well
BlueHat v18 || Memory resident implants - code injection is alive and wellBlueHat v18 || Memory resident implants - code injection is alive and well
BlueHat v18 || Memory resident implants - code injection is alive and well
 
BlueHat v18 || Massive scale usb device driver fuzz without device
BlueHat v18 || Massive scale usb device driver fuzz without deviceBlueHat v18 || Massive scale usb device driver fuzz without device
BlueHat v18 || Massive scale usb device driver fuzz without device
 
BlueHat v18 || Modern day entomology - examining the inner workings of the bu...
BlueHat v18 || Modern day entomology - examining the inner workings of the bu...BlueHat v18 || Modern day entomology - examining the inner workings of the bu...
BlueHat v18 || Modern day entomology - examining the inner workings of the bu...
 
BlueHat v18 || The matrix has you - protecting linux using deception
BlueHat v18 || The matrix has you - protecting linux using deceptionBlueHat v18 || The matrix has you - protecting linux using deception
BlueHat v18 || The matrix has you - protecting linux using deception
 
BlueHat v18 || An ice-cold boot to break bit locker
BlueHat v18 || An ice-cold boot to break bit lockerBlueHat v18 || An ice-cold boot to break bit locker
BlueHat v18 || An ice-cold boot to break bit locker
 

Recently uploaded

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAndikSusilo4
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?XfilesPro
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...HostedbyConfluent
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 

Recently uploaded (20)

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & Application
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 

BlueHat Seattle 2019 || The good, the bad & the ugly of ML based approaches for ransomware detection

  • 1.
  • 2. PRESENTERS: LI CHEN, RAVI SAHITA CONTRIBUTORS: LI CHEN, RAVI SAHITA, CHIH-YUAN YANG, ANINDYA PAUL Machine learning based ransomware detection: the good, the bad, and the ugly
  • 3. Legal Disclaimers • Intel provides these materials as-is, with no express or implied warranties. • All products, dates, and figures specified are preliminary, based on current expectations, and are subject to change without notice. • Intel processors, chipsets, and desktop boards may contain design defects or errors known as errata, which may cause the product to deviate from published specifications. Current characterized errata are available on request. • Intel technologies' features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration. No product or component can be absolutely secure. Check with your system manufacturer or retailer or learn more at http://intel.com. • Some results have been estimated or simulated using internal Intel analysis or architecture simulation or modeling, and provided to you for informational purposes. Any differences in your system hardware, software or configuration may affect your actual performance. • Intel and the Intel logo are trademarks of Intel Corporation in the United States and other countries. • *Other names and brands may be claimed as the property of others. © Intel Corporation 2019
  • 4. OUTLINE OF THE TALK • Ransomware detection case study • The Good: • Machine Learning (ML) is effective • The Bad: • ML can launch adversarial attacks on ML models • The Ugly: • ML Model durability • Improving detection via complementary platform capabilties
  • 5. What is Ransomware? • Ransomware is a category of malware which hijacks victim’s data or machine and demands monetary returns • Categories: • Locker-ransomware: hijack resources without encryption • Crypto-ransomware: deny access using encryption • The damage done by crypto-ransomware is irreversible in most cases due to the use of cryptography
  • 6. Typical Ransomware ACTIVITY Distribution Infection Communication EnumerationEncryptionExtortion
  • 7. Ransomware Data Description • Downloaded total ~22k ransomware using Microsoft and Kaspersky’s labels from VirusTotal • ~ 5min execution for each sample • Decoy files to identify activated crypto- ransomware - Identified ~4.4k active samples Ransomware families →
  • 8. DATA ACQUISITION VIA Sandbox System • Bare-metal system built on Windows*-based system • Refresh system by checkpointing SSD writes and restoring SSD partition image • Anti-evasion mechanisms • Simulated human activities • Opened applications • Limited heuristics Storage Control Server Storage Robot Internet Data storage Router Programmable Power Control … Robot
  • 9. Behavior Data BASED ON I/O Events • Collected Time stamp, I/O Event Type, Target Filename, Entropy • Based on C# .Net framework FileSystemWatcher • Entropy of target files calculated by normalized Shannon entropy
  • 10. The Good Machine learning can be efficient, scalable and accurate at recognizing malicious attacks.
  • 11. Feature extraction Events Feature encoding Padding 0 File deleted 1 File content changed and entropy is [0.9, 1] 2 File content changed and entropy is [0.2, 0.4) 3 File content changed and entropy is [0, 0.2) 4 File created 5 File content changed and entropy is [0.8, 0.9) 6 File renamed 7 File content changed and entropy is [0.4, 0.6) 8 File content changed and entropy is [0.6, 0.8) 9 • Each execution log is represented by a sequence of events. • We set the length = 3000 for each sample.
  • 12. ML model results for ransomware detection ❖Train-Test ratio: 0.8:0.2 ❖Training samples: 1292 benign, 3736 malicious ❖Test samples: 324 benign, 934 malicious ❖Dimensionality: n x 3000 ❖7 ML models We select Text CNN as feature extractor due to its superior performance compared with other classifiers.
  • 14. Features are well-separated in Text- CNN subspace Class-conditional density plot for each dimension in Text-CNN feature space.
  • 15. classifiers greatly improve in Text CNN feature subspace Classifiers improve up to 55% in accuracy in Text-CNN space.
  • 16. The Good - summary Machine learning is highly effective for malware detection. When ML classifiers are used in security-critical applications, are accuracy, FPR, precision, recall, F1 scores enough?
  • 17. The Bad Machine learning can hack vulnerable ML systems.
  • 18. Adversarial Machine Learning in Vision Object Detection (amplified) DNN: “Speed Limit Sign” DNN: “Ruler”Difference Image Classification https://arxiv.org/abs/1412.6572 https://arxiv.org/abs/1703.08603 Adversarial Pertubation Object detection on original image with adversarial pertubationObject detection on original image
  • 19. Generative Adversarial Network (GAN) Generator Discriminator G generates fakes to fool D D differentiates fakes and reals. Over time, G and D get better. Goodfellow, Ian, et al. "Generative adversarial nets." Advances in neural information processing systems. 2014.
  • 20. Core Idea: GAN to synthesize ransomware logs Our threat model assumes the adversary has access to training dataset but has no knowledge of the ML classifier.
  • 21. adversarial quality assessment A successful evasion means the generated malicious samples not only fool ransomware classifier, but also persists maliciousness based on certain metrics. We propose sample-based and batch-based adversarial quality metrics to evaluate
  • 23. GAN to bypass ransomware detection • We use the same training data to train AC-GAN • The stopping criterion is based on the loss of the discriminator • At test time, we generate 5000 malicious segments and ensure their adversarial quality
  • 24. Detection results on good quality adversarial examples Indicates a broad attack surface for ML
  • 25. THE BAD - SUMMARY Machine learning can automatically hack other highly effective ML systems. Generative adversarial network can serve as an intelligent hacker to bypass effective systems. Robustness and resiliency are equally important as accuracy, FPR, precision, recall, F1 scores. Why does this happen?
  • 26. The Ugly The investigation Concept drift Time variant samples
  • 27. Investigation We investigate why the generated samples can bypass ML detection The generated samples, in dark red, lie close to a linear boundary but much closer to the real benign samples in the Text-CNN latent feature subspace
  • 28. Non-linear boundary decision shows to be more robust • SVM with radial basis in Text-CNN space was able to detect all the adversarial examples • The non-linear boundary decision pertain robustness and indicates a smaller blindspot
  • 29. Other issues • Concept drift • Time variant
  • 30. The Ugly - summary: Investigation of ML boundaries indicates adversarial samples lie close to the benign samples in feature subspace. Nonlinear boundary decisions show better resiliency against adversarial examples.
  • 32. Intel Labs Analytical to real-world samples How to take the output of GAN and incorporate it in the tool to run ransomware?
  • 33. PLATFORM capabilities to make ML system more trustworthy • Can we use ML + system capabilities to make the attackers’ job harder? • Intel® Processor Trace and other telemetry can be used to make the system call activity information more trustworthy • Checkpointing technologies are a useful tool for recovery • Trusted Execution capabilities can prevent model stealing attacks • New storage mechanisms (such as persistent memory) provide new avenues for access-control
  • 34. Backup Ransomware Mitigation Ransomware ML DetectorRollback File IO Events, Entropy, Path Early Detection USE ML AS AN EARLY DETECTOR
  • 35. ML VULNERABILITY RESEARCH PLATFORM - MLsploit • A Cloud-Based Framework for Adversarial Machine Learning Research • Tool for interactive investigation of ML vulnerabilities • Interactive interface and iterative experimentation • Comparison for attack and defenses
  • 36. SUMMARY • ML can be used to build efficient, scalable and accurate at recognizing malicious attacks such as ransomware • ML can also be used to hack vulnerable ML systems • ML models must comprehend adversarial approaches, concept drift and time variations • Combing platform capabilities for attack surface reduction (prevention) and recovery capabilities can complement ML detection for robust solutions
  • 39. 39
  • 40. The intersection of AI & Security 40 Security Analytics Secure AI Workloads Adversarial Resilient AI Today’s focus
  • 41. Case Study • Collect real ransomware and benign software • Examine ML effectiveness for ransomware detection • Explore ML robustness when ML generates adversarial ransomware samples • Investigate ML blind spot and boundaries
  • 42. classifiers greatly improve in Text CNN feature subspace
  • 43. 43 Beyond vision: audio or malware Attack in ASR domain on audio waveforms to fool DeepSpeech (speech-to-text transcription) AVPASS: adversarial malwares variants that can beat VirusTotal detection https://arxiv.org/abs/1801.01944 https://www.blackhat.com/us-17/briefings/schedule/#avpass-leaking-and-bypassing-antivirus-detection-model-automatically-7354 Bypass VirusTotal up to 100%
  • 44. Training GAN Challenges: ❖Convergence issue: ❖Transfer learning ❖Learning rates adapted for generator and discriminaro • We use the same training data to train AC-GAN • The stopping criterion is based on the loss of the discriminator • At test time, we generate 5000 malicious segments 44
  • 45. adversarial quality metric Batch-basedSample-based Indicates the generated samples are much more alike malicious real ransomware samples
  • 46. Distribution difference in original and feature space