SlideShare una empresa de Scribd logo
1 de 22
Descargar para leer sin conexión
© 2019 Intel
AI Reliability Against
Adversarial Inputs
Gokcen Cilingir, Li Chen
Intel
May 2019
© 2019 Intel
Motivation
Adversarial examples are already seen in our daily life.
Designing AI solutions that are robust against adversarial inputs is important
for
• [Security] Critical system asset management and defense against
malware
• [Reliability] Ensuring consistent and reliable system behavior
2
AI-based
malware
detector
PASS
Automated
Speech
Recognition
Adversarial input
“A B C” “X Y Z”
Faulty prediction
© 2019 Intel
How big can the damage be?
3
© 2019 Intel
Adversarial attack examples
From malware detection to other domains
Face recognition
4Image source: [1]
© 2019 Intel
Adversarial attack examples
Autonomous driving
5
Image source: [2]
© 2019 Intel
Adversarial attack examples
Automated speech recognition
6Image source: [3]
© 2019 Intel
How does it work?
7
© 2019 Intel
Adversarial ML concepts
8
A taxonomy of adversaries against machine learning models at test time
(with evasion as the goal)
Image source: [6]
• Evasion vs. Data
poisoning attacks
• Threat models
• Substitute model
creation and
transferability
© 2019 Intel
Adversarial example creation
• The very tool that makes ML powerful is being used to break it: optimization
• An adversarial example x* is found by perturbing an originally correctly classified input x by
(approximately) solving the following constrained optimization problem. t is the target class.
9
Added noise
magnified by 10x
Prediction:
School bus
Prediction:
Ostrich
Image source: [4], Text adopted:[5]
© 2019 Intel
How has Machine Learning been Exploited?
• Take binary classification as an example. Through training, one can generally learn only an
approximation of the true boundaries.
• The model error between the approximate and expected decision boundaries is exploited by
adversaries as illustrated in the following figure:
10
Image source, text adopted: [5]
© 2019 Intel
Defense and mitigation
11
© 2019 Intel
High level flow for AI-based solutions
12
AI inferenceInput
Prediction &
confidence Action
determination
Action
AI model
definition and
training
Training
dataset
AI model
CLIENT
CLOUD
AI-based application
© 2019 Intel
Defense and mitigation against adversarial attacks
13
AI inferenceInput
Prediction &
confidence Action
determination
Action
Adversary aware AI model
definition and training
Training
dataset
Strengthened AI model
CLIENT
CLOUD
AI-based application
Pre-processing for
perturbation
removal
Input validation
/Adversary
detection
Mitigation
policy
Examples: Adversarial training,
defensive distillation, logit pairing,
architectural modifications like BNNs
Examples: JPEG
compression, SHIELD,
MP3 audio compression
Examples: Distributional detection,
normalization detection, PCA-based
detection, secondary classification
Robustness metric
© 2019 Intel
Defenses and their limitations
• Current status: Race continues between attackers and defenses. All known defense
techniques come with limitations.
• Adversarial training uses generated adversarial examples as part of training
• Architectures like Bayesian NNs provide better uncertainty modeling
• Detection and pre-processing methods are generally domain specific.
• SHIELD compresses away small pixel manipulations over images, MP3 audio
compression applies the same idea over audio data.
14
© 2019 Intel
Tools for attack simulations and
defenses
15
© 2019 Intel
MLsploit: A Cloud-Based Framework for Adversarial
Machine Learning Research
16
• Research module for adversarial machine learning
• Interactive interface and experimentation
• Comparison for attack and defenses
• Easy integration
© 2019 Intel 17
© 2019 Intel 18
Toolkits
• Adversarial Robustness Toolbox (ART): Python library for adversarial
attacks and defenses (evasion, poisoning) for NNs. Also supplies access
to robustness metrics.
• Cleverhans: An adversarial example library for constructing attacks,
building defenses, and benchmarking both.
• ALFASVMLib: An open-source Matlab library that implements a set of
heuristic attacks against Support Vector Machines (SVMs).
• Foolbox: A Python toolbox to create adversarial examples that fool neural
networks in PyTorch, TensorFlow, Keras, MxNet, ..
• MLsploit: A web platform to demo Machine Learning as a Service on
security researches. A portal to demo adversarial ML and
countermeasures is provided.
© 2019 Intel
Conclusion
• ML can be vulnerable to adversarial examples.
• Designing AI solutions that are robust against adversarial inputs is
important for security and reliability of critical applications.
• Several free and open-sourced toolkits exist to assess and strengthen AI
models.
19
© 2019 Intel
Resources
20
[1] Sharif, Mahmood, et al. "Accessorize to a crime: Real and stealthy attacks on state-of-the-art face
recognition." Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications
Security. ACM, 2016.
[2] Metzen, Jan Hendrik, et al. "Universal adversarial perturbations against semantic image
segmentation." 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, 2017.
[3] Carlini, Nicholas, and David Wagner. "Audio adversarial examples: Targeted attacks on speech-to-
text." 2018 IEEE Security and Privacy Workshops (SPW). IEEE, 2018.
[4] Szegedy, Christian, et al. "Intriguing properties of neural networks." arXiv preprint
arXiv:1312.6199 (2013).
[5] Goodfellow, Ian, Patrick McDaniel, and Nicolas Papernot. "Making machine learning robust against
adversarial inputs." Communications of the ACM 61.7 (2018): 56-66.
[6] Papernot, Nicolas, et al. "The limitations of deep learning in adversarial settings." 2016 IEEE
European Symposium on Security and Privacy (EuroS&P). IEEE, 2016.
[7] Das, Nilaksh, et al. "Shield: Fast, practical defense and vaccination for deep learning using jpeg
compression." Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &
Data Mining. ACM, 2018.
[8] Das, Nilaksh, et al. "ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for
Audio." Joint European Conference on Machine Learning and Knowledge Discovery in Databases.
Springer, Cham, 2018.
© 2019 Intel
Glossary
• Adversarial example: Inputs that have been intentionally optimized to cause misclassification
• Threat models in the context of adversarial ML refers to the explicit definition of the capabilities
of the adversary
• White-box threat model: An adversary with an access to (at minimum) the model architecture
and the parameter values.
• Black-box threat model: An adversary with an access to either just the samples or the oracle
(system output is visible)
• Adversarial sample transferability: The property that adversarial samples produced by training
on a specific model can affect another model, even if they have different architectures and/or
training data
• Evasion attack: The adversary tries to evade the system by adjusting malicious samples during
testing phase
• Data poisoning attack: An adversary tries to poison the training data by injecting carefully
designed samples to compromise the learning process
21
© 2019 Intel
Legal Disclaimers
▪Intel provides these materials as-is, with no express or implied warranties.
▪Intel products 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 computer system can be absolutely secure. Check with your system
manufacturer or retailer or learn more at http://intel.com.
▪No license (express or implied, by estoppel or otherwise) to any intellectual property rights
is granted by this document.
Copyright © 2019 Intel Corporation. All rights reserved. Intel, the Intel logo and others are
trademarks of Intel Corporation in the U.S. and/or other countries.
22

Más contenido relacionado

Más de Edge AI and Vision Alliance

“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
Edge AI and Vision Alliance
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
Edge AI and Vision Alliance
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
Edge AI and Vision Alliance
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
Edge AI and Vision Alliance
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
Edge AI and Vision Alliance
 
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
Edge AI and Vision Alliance
 
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
Edge AI and Vision Alliance
 
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ..."Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
Edge AI and Vision Alliance
 
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
Edge AI and Vision Alliance
 
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
Edge AI and Vision Alliance
 

Más de Edge AI and Vision Alliance (20)

“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
 
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
 
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
 
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
 
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
 
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ..."Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
 
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
 
“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from Instrumental“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from Instrumental
 
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
 

Último

Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Victor Rentea
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 

Último (20)

Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 

"AI Reliability Against Adversarial Inputs," a Presentation from Intel

  • 1. © 2019 Intel AI Reliability Against Adversarial Inputs Gokcen Cilingir, Li Chen Intel May 2019
  • 2. © 2019 Intel Motivation Adversarial examples are already seen in our daily life. Designing AI solutions that are robust against adversarial inputs is important for • [Security] Critical system asset management and defense against malware • [Reliability] Ensuring consistent and reliable system behavior 2 AI-based malware detector PASS Automated Speech Recognition Adversarial input “A B C” “X Y Z” Faulty prediction
  • 3. © 2019 Intel How big can the damage be? 3
  • 4. © 2019 Intel Adversarial attack examples From malware detection to other domains Face recognition 4Image source: [1]
  • 5. © 2019 Intel Adversarial attack examples Autonomous driving 5 Image source: [2]
  • 6. © 2019 Intel Adversarial attack examples Automated speech recognition 6Image source: [3]
  • 7. © 2019 Intel How does it work? 7
  • 8. © 2019 Intel Adversarial ML concepts 8 A taxonomy of adversaries against machine learning models at test time (with evasion as the goal) Image source: [6] • Evasion vs. Data poisoning attacks • Threat models • Substitute model creation and transferability
  • 9. © 2019 Intel Adversarial example creation • The very tool that makes ML powerful is being used to break it: optimization • An adversarial example x* is found by perturbing an originally correctly classified input x by (approximately) solving the following constrained optimization problem. t is the target class. 9 Added noise magnified by 10x Prediction: School bus Prediction: Ostrich Image source: [4], Text adopted:[5]
  • 10. © 2019 Intel How has Machine Learning been Exploited? • Take binary classification as an example. Through training, one can generally learn only an approximation of the true boundaries. • The model error between the approximate and expected decision boundaries is exploited by adversaries as illustrated in the following figure: 10 Image source, text adopted: [5]
  • 11. © 2019 Intel Defense and mitigation 11
  • 12. © 2019 Intel High level flow for AI-based solutions 12 AI inferenceInput Prediction & confidence Action determination Action AI model definition and training Training dataset AI model CLIENT CLOUD AI-based application
  • 13. © 2019 Intel Defense and mitigation against adversarial attacks 13 AI inferenceInput Prediction & confidence Action determination Action Adversary aware AI model definition and training Training dataset Strengthened AI model CLIENT CLOUD AI-based application Pre-processing for perturbation removal Input validation /Adversary detection Mitigation policy Examples: Adversarial training, defensive distillation, logit pairing, architectural modifications like BNNs Examples: JPEG compression, SHIELD, MP3 audio compression Examples: Distributional detection, normalization detection, PCA-based detection, secondary classification Robustness metric
  • 14. © 2019 Intel Defenses and their limitations • Current status: Race continues between attackers and defenses. All known defense techniques come with limitations. • Adversarial training uses generated adversarial examples as part of training • Architectures like Bayesian NNs provide better uncertainty modeling • Detection and pre-processing methods are generally domain specific. • SHIELD compresses away small pixel manipulations over images, MP3 audio compression applies the same idea over audio data. 14
  • 15. © 2019 Intel Tools for attack simulations and defenses 15
  • 16. © 2019 Intel MLsploit: A Cloud-Based Framework for Adversarial Machine Learning Research 16 • Research module for adversarial machine learning • Interactive interface and experimentation • Comparison for attack and defenses • Easy integration
  • 18. © 2019 Intel 18 Toolkits • Adversarial Robustness Toolbox (ART): Python library for adversarial attacks and defenses (evasion, poisoning) for NNs. Also supplies access to robustness metrics. • Cleverhans: An adversarial example library for constructing attacks, building defenses, and benchmarking both. • ALFASVMLib: An open-source Matlab library that implements a set of heuristic attacks against Support Vector Machines (SVMs). • Foolbox: A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, Keras, MxNet, .. • MLsploit: A web platform to demo Machine Learning as a Service on security researches. A portal to demo adversarial ML and countermeasures is provided.
  • 19. © 2019 Intel Conclusion • ML can be vulnerable to adversarial examples. • Designing AI solutions that are robust against adversarial inputs is important for security and reliability of critical applications. • Several free and open-sourced toolkits exist to assess and strengthen AI models. 19
  • 20. © 2019 Intel Resources 20 [1] Sharif, Mahmood, et al. "Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition." Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. ACM, 2016. [2] Metzen, Jan Hendrik, et al. "Universal adversarial perturbations against semantic image segmentation." 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, 2017. [3] Carlini, Nicholas, and David Wagner. "Audio adversarial examples: Targeted attacks on speech-to- text." 2018 IEEE Security and Privacy Workshops (SPW). IEEE, 2018. [4] Szegedy, Christian, et al. "Intriguing properties of neural networks." arXiv preprint arXiv:1312.6199 (2013). [5] Goodfellow, Ian, Patrick McDaniel, and Nicolas Papernot. "Making machine learning robust against adversarial inputs." Communications of the ACM 61.7 (2018): 56-66. [6] Papernot, Nicolas, et al. "The limitations of deep learning in adversarial settings." 2016 IEEE European Symposium on Security and Privacy (EuroS&P). IEEE, 2016. [7] Das, Nilaksh, et al. "Shield: Fast, practical defense and vaccination for deep learning using jpeg compression." Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2018. [8] Das, Nilaksh, et al. "ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio." Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Cham, 2018.
  • 21. © 2019 Intel Glossary • Adversarial example: Inputs that have been intentionally optimized to cause misclassification • Threat models in the context of adversarial ML refers to the explicit definition of the capabilities of the adversary • White-box threat model: An adversary with an access to (at minimum) the model architecture and the parameter values. • Black-box threat model: An adversary with an access to either just the samples or the oracle (system output is visible) • Adversarial sample transferability: The property that adversarial samples produced by training on a specific model can affect another model, even if they have different architectures and/or training data • Evasion attack: The adversary tries to evade the system by adjusting malicious samples during testing phase • Data poisoning attack: An adversary tries to poison the training data by injecting carefully designed samples to compromise the learning process 21
  • 22. © 2019 Intel Legal Disclaimers ▪Intel provides these materials as-is, with no express or implied warranties. ▪Intel products 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 computer system can be absolutely secure. Check with your system manufacturer or retailer or learn more at http://intel.com. ▪No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document. Copyright © 2019 Intel Corporation. All rights reserved. Intel, the Intel logo and others are trademarks of Intel Corporation in the U.S. and/or other countries. 22