SlideShare una empresa de Scribd logo
1 de 20
Descargar para leer sin conexión
Listener Anonymizer:
Camouflaging Play Logs
to Preserve User’s Demographic Anonymity
Kosetsu Tsukuda, Satoru Fukayama, Masataka Goto
National Institute of Advanced Industrial Science and Technology (AIST), Japan
Sept. 26, 2018
I love music recommendation
Music recommendation can improve user’s music experience
 To improve recommendation accuracy, it is beneficial to
predict user’s demographic attributes (age, gender, nationality)
 A user’s demographics can be predicted with high accuracy
by using the user’s play log
𝑡𝑡
Your nationality is
Age Gender Nationality
4.13mean absolute error 77.01%accuracy 69.37%accuracy
T. Krismayer, M. Schedl, P. Knees, R. Rabiser
Prediction of User Demographics from Music Listening Habits
CBMI 2017
Play log
Technique to leverage play logs
for predicting users' demographic attributes
?
COUNTERBALANCE
Technique to leverage play logs
for predicting users' demographic attributes
Technique to camouflage play logs
for preserving users' demographic anonymity
COUNTERBALANCE
Listener Anonymizer
𝑡𝑡
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
𝑡𝑡
Listener Anonymizer
…
Compute
a probability distribution
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
𝑡𝑡
Listener Anonymizer
Compute
a probability distribution
…
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
𝑡𝑡
Listener Anonymizer
Compute
a probability distribution
…
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
𝑡𝑡
Listener Anonymizer
Compute
a probability distribution
…
…
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
𝑡𝑡
Listener Anonymizer
Compute
a probability distribution
…
Listener Anonymizer
Your nationality can be predicted
as French with a probability of 67%
Anonymize
…
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
𝑡𝑡
Listener Anonymizer
Compute
a probability distribution
…
…
0.21 0.04 0.77 0.89
0.48 0.92 0.25 0.33
0.82 0.29 0.46 0.86
𝑢𝑢1
𝑢𝑢2
𝑢𝑢𝑟𝑟
𝑠𝑠1 𝑠𝑠2 𝑠𝑠3 𝑠𝑠𝑚𝑚… …
Compute the effectiveness of each song
to anonymize her nationality
𝑢𝑢𝑖𝑖: user
𝑠𝑠𝑗𝑗: song
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
𝑡𝑡
Listener Anonymizer
Compute
a probability distribution
…
…
0.21 0.04 0.77 0.89
0.48 0.92 0.25 0.33
0.82 0.29 0.46 0.86
𝑢𝑢1
𝑢𝑢2
𝑢𝑢𝑟𝑟
𝑠𝑠1 𝑠𝑠2 𝑠𝑠3 𝑠𝑠𝑚𝑚… …
Compute the effectiveness of each song
to anonymize her nationality
Listener Anonymizer
Recommendations:
Play
𝑢𝑢𝑖𝑖: user
𝑠𝑠𝑗𝑗: song
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
𝑡𝑡
Listener Anonymizer
Compute
a probability distribution
…
…
0.21 0.04 0.77 0.89
0.48 0.92 0.25 0.33
0.82 0.29 0.46 0.86
𝑢𝑢1
𝑢𝑢2
𝑢𝑢𝑟𝑟
𝑠𝑠1 𝑠𝑠2 𝑠𝑠3 𝑠𝑠𝑚𝑚… …
Compute the effectiveness of each song
to anonymize her nationality
𝑢𝑢𝑖𝑖: user
𝑠𝑠𝑗𝑗: song
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
…
𝑡𝑡
Listener Anonymizer
Compute
a probability distribution
…
0.21 0.04 0.77 0.89
0.48 0.92 0.25 0.33
0.82 0.29 0.46 0.86
𝑢𝑢1
𝑢𝑢2
𝑢𝑢𝑟𝑟
𝑠𝑠1 𝑠𝑠2 𝑠𝑠3 𝑠𝑠𝑚𝑚… …
Compute the effectiveness of each song
to anonymize her nationality
Your nationality is … ??
𝑢𝑢𝑖𝑖: user
𝑠𝑠𝑗𝑗: song
 Emma is a 22-year-old French female
 She uses both an online music service and Listener Anonymizer
 She concealed her nationality when she signed up to the service
Age Gender Nationality
3.22songs 9.28songs 4.36songs
𝑡𝑡
…
Avg number of songs for camouflaging play logs
30 songs
Probability When a user plays 30 songs,
the distribution is strongly biased to Polish (the left most graph)
 She can camouflage her play log by playing only three songs
recommended by Listener Anonymizer
I can enjoy music while preserving
my demographic anonymity!
Without Listener Anonymizer With Listener Anonymizer
 It is important to show that
preserving users’ demographic anonymity is technically possible
 Listener Anonymizer gives a choice to a user
Demographic
anonymity
High rec.
accuracy
I do not care about
my demographic anonymity!
 Listener Anonymizer might degrade recommendation accuracy
 We dared to propose this controversial approach
to raise privacy issues in the ISMIR community

Más contenido relacionado

Más de Kosetsu Tsukuda

繰り返し消費されるコンテンツを対象とした推薦理由の提示(IFAT142・登壇発表)
繰り返し消費されるコンテンツを対象とした推薦理由の提示(IFAT142・登壇発表)繰り返し消費されるコンテンツを対象とした推薦理由の提示(IFAT142・登壇発表)
繰り返し消費されるコンテンツを対象とした推薦理由の提示(IFAT142・登壇発表)Kosetsu Tsukuda
 
Kiite Cafe: 同じ楽曲を同じ瞬間に楽しんで「好き」が伝わる音楽発掘カフェ(SIGMUS132・登壇発表)
Kiite Cafe: 同じ楽曲を同じ瞬間に楽しんで「好き」が伝わる音楽発掘カフェ(SIGMUS132・登壇発表)Kiite Cafe: 同じ楽曲を同じ瞬間に楽しんで「好き」が伝わる音楽発掘カフェ(SIGMUS132・登壇発表)
Kiite Cafe: 同じ楽曲を同じ瞬間に楽しんで「好き」が伝わる音楽発掘カフェ(SIGMUS132・登壇発表)Kosetsu Tsukuda
 
Explainable Recommendation for Repeat Consumption(RecSys2020論文読み会)
Explainable Recommendation for Repeat Consumption(RecSys2020論文読み会)Explainable Recommendation for Repeat Consumption(RecSys2020論文読み会)
Explainable Recommendation for Repeat Consumption(RecSys2020論文読み会)Kosetsu Tsukuda
 
Explainable Recommendation for Repeat Consumption (RecSys 2020)
Explainable Recommendation for Repeat Consumption (RecSys 2020)Explainable Recommendation for Repeat Consumption (RecSys 2020)
Explainable Recommendation for Repeat Consumption (RecSys 2020)Kosetsu Tsukuda
 
Query/Task Satisfaction and Grid-based Evaluation Metrics Under Different Ima...
Query/Task Satisfaction and Grid-based Evaluation Metrics Under Different Ima...Query/Task Satisfaction and Grid-based Evaluation Metrics Under Different Ima...
Query/Task Satisfaction and Grid-based Evaluation Metrics Under Different Ima...Kosetsu Tsukuda
 
The Web Conference 2020 国際会議報告(ACM SIGMOD 日本支部第73回支部大会・依頼講演)
The Web Conference 2020 国際会議報告(ACM SIGMOD 日本支部第73回支部大会・依頼講演)The Web Conference 2020 国際会議報告(ACM SIGMOD 日本支部第73回支部大会・依頼講演)
The Web Conference 2020 国際会議報告(ACM SIGMOD 日本支部第73回支部大会・依頼講演)Kosetsu Tsukuda
 
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...Kosetsu Tsukuda
 
ABCPRec:何を創作したかという情報がコンテンツの消費時に反映されるユーザ生成コンテンツ推薦手法(WebDB Forum 2019・登壇発表)
ABCPRec:何を創作したかという情報がコンテンツの消費時に反映されるユーザ生成コンテンツ推薦手法(WebDB Forum 2019・登壇発表)ABCPRec:何を創作したかという情報がコンテンツの消費時に反映されるユーザ生成コンテンツ推薦手法(WebDB Forum 2019・登壇発表)
ABCPRec:何を創作したかという情報がコンテンツの消費時に反映されるユーザ生成コンテンツ推薦手法(WebDB Forum 2019・登壇発表)Kosetsu Tsukuda
 
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...Kosetsu Tsukuda
 
ABCPRec:ユーザの消費者としての役割と創作者としての役割の適応的対応付けによるユーザ生成コンテンツ推薦(第14回WI2研究会)
ABCPRec:ユーザの消費者としての役割と創作者としての役割の適応的対応付けによるユーザ生成コンテンツ推薦(第14回WI2研究会)ABCPRec:ユーザの消費者としての役割と創作者としての役割の適応的対応付けによるユーザ生成コンテンツ推薦(第14回WI2研究会)
ABCPRec:ユーザの消費者としての役割と創作者としての役割の適応的対応付けによるユーザ生成コンテンツ推薦(第14回WI2研究会)Kosetsu Tsukuda
 
ABCPRec: Adaptively Bridging Consumer and Producer Roles for User-Generated C...
ABCPRec: Adaptively Bridging Consumer and Producer Roles for User-Generated C...ABCPRec: Adaptively Bridging Consumer and Producer Roles for User-Generated C...
ABCPRec: Adaptively Bridging Consumer and Producer Roles for User-Generated C...Kosetsu Tsukuda
 
Lyric Jumper: A Lyrics-Based Music Exploratory Web Service by Modeling Lyrics...
Lyric Jumper: A Lyrics-Based Music Exploratory Web Service by Modeling Lyrics...Lyric Jumper: A Lyrics-Based Music Exploratory Web Service by Modeling Lyrics...
Lyric Jumper: A Lyrics-Based Music Exploratory Web Service by Modeling Lyrics...Kosetsu Tsukuda
 
Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic An...
Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic An...Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic An...
Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic An...Kosetsu Tsukuda
 
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づき様々な歌詞に出会える歌詞探索サービス
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づき様々な歌詞に出会える歌詞探索サービス Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づき様々な歌詞に出会える歌詞探索サービス
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づき様々な歌詞に出会える歌詞探索サービス Kosetsu Tsukuda
 
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づく歌詞探索サービス
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づく歌詞探索サービスLyric Jumper:アーティストごとの歌詞トピックの傾向に基づく歌詞探索サービス
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づく歌詞探索サービスKosetsu Tsukuda
 
Taste or Addiction?: Using Play Logs to Infer Song Selection Motivation
Taste or Addiction?: Using Play Logs to Infer Song Selection MotivationTaste or Addiction?: Using Play Logs to Infer Song Selection Motivation
Taste or Addiction?: Using Play Logs to Infer Song Selection MotivationKosetsu Tsukuda
 
SmartVideoRanking: 視聴者の時刻同期コメントに基づく動画ランキングシステム
SmartVideoRanking: 視聴者の時刻同期コメントに基づく動画ランキングシステムSmartVideoRanking: 視聴者の時刻同期コメントに基づく動画ランキングシステム
SmartVideoRanking: 視聴者の時刻同期コメントに基づく動画ランキングシステムKosetsu Tsukuda
 
Why Did You Cover That Song?: Modeling N-th Order Derivative Creation with Co...
Why Did You Cover That Song?: Modeling N-th Order Derivative Creation with Co...Why Did You Cover That Song?: Modeling N-th Order Derivative Creation with Co...
Why Did You Cover That Song?: Modeling N-th Order Derivative Creation with Co...Kosetsu Tsukuda
 
コンテンツの人気度を考慮したN次創作活動のモデル化
コンテンツの人気度を考慮したN次創作活動のモデル化コンテンツの人気度を考慮したN次創作活動のモデル化
コンテンツの人気度を考慮したN次創作活動のモデル化Kosetsu Tsukuda
 
コンテンツの人気度を考慮したN次創作活動のモデル化(ポスター)
コンテンツの人気度を考慮したN次創作活動のモデル化(ポスター)コンテンツの人気度を考慮したN次創作活動のモデル化(ポスター)
コンテンツの人気度を考慮したN次創作活動のモデル化(ポスター)Kosetsu Tsukuda
 

Más de Kosetsu Tsukuda (20)

繰り返し消費されるコンテンツを対象とした推薦理由の提示(IFAT142・登壇発表)
繰り返し消費されるコンテンツを対象とした推薦理由の提示(IFAT142・登壇発表)繰り返し消費されるコンテンツを対象とした推薦理由の提示(IFAT142・登壇発表)
繰り返し消費されるコンテンツを対象とした推薦理由の提示(IFAT142・登壇発表)
 
Kiite Cafe: 同じ楽曲を同じ瞬間に楽しんで「好き」が伝わる音楽発掘カフェ(SIGMUS132・登壇発表)
Kiite Cafe: 同じ楽曲を同じ瞬間に楽しんで「好き」が伝わる音楽発掘カフェ(SIGMUS132・登壇発表)Kiite Cafe: 同じ楽曲を同じ瞬間に楽しんで「好き」が伝わる音楽発掘カフェ(SIGMUS132・登壇発表)
Kiite Cafe: 同じ楽曲を同じ瞬間に楽しんで「好き」が伝わる音楽発掘カフェ(SIGMUS132・登壇発表)
 
Explainable Recommendation for Repeat Consumption(RecSys2020論文読み会)
Explainable Recommendation for Repeat Consumption(RecSys2020論文読み会)Explainable Recommendation for Repeat Consumption(RecSys2020論文読み会)
Explainable Recommendation for Repeat Consumption(RecSys2020論文読み会)
 
Explainable Recommendation for Repeat Consumption (RecSys 2020)
Explainable Recommendation for Repeat Consumption (RecSys 2020)Explainable Recommendation for Repeat Consumption (RecSys 2020)
Explainable Recommendation for Repeat Consumption (RecSys 2020)
 
Query/Task Satisfaction and Grid-based Evaluation Metrics Under Different Ima...
Query/Task Satisfaction and Grid-based Evaluation Metrics Under Different Ima...Query/Task Satisfaction and Grid-based Evaluation Metrics Under Different Ima...
Query/Task Satisfaction and Grid-based Evaluation Metrics Under Different Ima...
 
The Web Conference 2020 国際会議報告(ACM SIGMOD 日本支部第73回支部大会・依頼講演)
The Web Conference 2020 国際会議報告(ACM SIGMOD 日本支部第73回支部大会・依頼講演)The Web Conference 2020 国際会議報告(ACM SIGMOD 日本支部第73回支部大会・依頼講演)
The Web Conference 2020 国際会議報告(ACM SIGMOD 日本支部第73回支部大会・依頼講演)
 
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
 
ABCPRec:何を創作したかという情報がコンテンツの消費時に反映されるユーザ生成コンテンツ推薦手法(WebDB Forum 2019・登壇発表)
ABCPRec:何を創作したかという情報がコンテンツの消費時に反映されるユーザ生成コンテンツ推薦手法(WebDB Forum 2019・登壇発表)ABCPRec:何を創作したかという情報がコンテンツの消費時に反映されるユーザ生成コンテンツ推薦手法(WebDB Forum 2019・登壇発表)
ABCPRec:何を創作したかという情報がコンテンツの消費時に反映されるユーザ生成コンテンツ推薦手法(WebDB Forum 2019・登壇発表)
 
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
DualDiv: Diversifying Items and Explanation Styles in Explainable Hybrid Reco...
 
ABCPRec:ユーザの消費者としての役割と創作者としての役割の適応的対応付けによるユーザ生成コンテンツ推薦(第14回WI2研究会)
ABCPRec:ユーザの消費者としての役割と創作者としての役割の適応的対応付けによるユーザ生成コンテンツ推薦(第14回WI2研究会)ABCPRec:ユーザの消費者としての役割と創作者としての役割の適応的対応付けによるユーザ生成コンテンツ推薦(第14回WI2研究会)
ABCPRec:ユーザの消費者としての役割と創作者としての役割の適応的対応付けによるユーザ生成コンテンツ推薦(第14回WI2研究会)
 
ABCPRec: Adaptively Bridging Consumer and Producer Roles for User-Generated C...
ABCPRec: Adaptively Bridging Consumer and Producer Roles for User-Generated C...ABCPRec: Adaptively Bridging Consumer and Producer Roles for User-Generated C...
ABCPRec: Adaptively Bridging Consumer and Producer Roles for User-Generated C...
 
Lyric Jumper: A Lyrics-Based Music Exploratory Web Service by Modeling Lyrics...
Lyric Jumper: A Lyrics-Based Music Exploratory Web Service by Modeling Lyrics...Lyric Jumper: A Lyrics-Based Music Exploratory Web Service by Modeling Lyrics...
Lyric Jumper: A Lyrics-Based Music Exploratory Web Service by Modeling Lyrics...
 
Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic An...
Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic An...Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic An...
Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic An...
 
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づき様々な歌詞に出会える歌詞探索サービス
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づき様々な歌詞に出会える歌詞探索サービス Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づき様々な歌詞に出会える歌詞探索サービス
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づき様々な歌詞に出会える歌詞探索サービス
 
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づく歌詞探索サービス
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づく歌詞探索サービスLyric Jumper:アーティストごとの歌詞トピックの傾向に基づく歌詞探索サービス
Lyric Jumper:アーティストごとの歌詞トピックの傾向に基づく歌詞探索サービス
 
Taste or Addiction?: Using Play Logs to Infer Song Selection Motivation
Taste or Addiction?: Using Play Logs to Infer Song Selection MotivationTaste or Addiction?: Using Play Logs to Infer Song Selection Motivation
Taste or Addiction?: Using Play Logs to Infer Song Selection Motivation
 
SmartVideoRanking: 視聴者の時刻同期コメントに基づく動画ランキングシステム
SmartVideoRanking: 視聴者の時刻同期コメントに基づく動画ランキングシステムSmartVideoRanking: 視聴者の時刻同期コメントに基づく動画ランキングシステム
SmartVideoRanking: 視聴者の時刻同期コメントに基づく動画ランキングシステム
 
Why Did You Cover That Song?: Modeling N-th Order Derivative Creation with Co...
Why Did You Cover That Song?: Modeling N-th Order Derivative Creation with Co...Why Did You Cover That Song?: Modeling N-th Order Derivative Creation with Co...
Why Did You Cover That Song?: Modeling N-th Order Derivative Creation with Co...
 
コンテンツの人気度を考慮したN次創作活動のモデル化
コンテンツの人気度を考慮したN次創作活動のモデル化コンテンツの人気度を考慮したN次創作活動のモデル化
コンテンツの人気度を考慮したN次創作活動のモデル化
 
コンテンツの人気度を考慮したN次創作活動のモデル化(ポスター)
コンテンツの人気度を考慮したN次創作活動のモデル化(ポスター)コンテンツの人気度を考慮したN次創作活動のモデル化(ポスター)
コンテンツの人気度を考慮したN次創作活動のモデル化(ポスター)
 

Último

development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusNazaninKarimi6
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsSérgio Sacani
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and ClassificationsAreesha Ahmad
 
Exploring Criminology and Criminal Behaviour.pdf
Exploring Criminology and Criminal Behaviour.pdfExploring Criminology and Criminal Behaviour.pdf
Exploring Criminology and Criminal Behaviour.pdfrohankumarsinghrore1
 
Stages in the normal growth curve
Stages in the normal growth curveStages in the normal growth curve
Stages in the normal growth curveAreesha Ahmad
 
Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Silpa
 
An introduction on sequence tagged site mapping
An introduction on sequence tagged site mappingAn introduction on sequence tagged site mapping
An introduction on sequence tagged site mappingadibshanto115
 
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxPSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxSuji236384
 
COMPUTING ANTI-DERIVATIVES (Integration by SUBSTITUTION)
COMPUTING ANTI-DERIVATIVES(Integration by SUBSTITUTION)COMPUTING ANTI-DERIVATIVES(Integration by SUBSTITUTION)
COMPUTING ANTI-DERIVATIVES (Integration by SUBSTITUTION)AkefAfaneh2
 
Introduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptxIntroduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptxrohankumarsinghrore1
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxseri bangash
 
GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)Areesha Ahmad
 
biology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGYbiology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGY1301aanya
 
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.Silpa
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .Poonam Aher Patil
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)Areesha Ahmad
 
Velocity and Acceleration PowerPoint.ppt
Velocity and Acceleration PowerPoint.pptVelocity and Acceleration PowerPoint.ppt
Velocity and Acceleration PowerPoint.pptRakeshMohan42
 

Último (20)

development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virus
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
 
Exploring Criminology and Criminal Behaviour.pdf
Exploring Criminology and Criminal Behaviour.pdfExploring Criminology and Criminal Behaviour.pdf
Exploring Criminology and Criminal Behaviour.pdf
 
Stages in the normal growth curve
Stages in the normal growth curveStages in the normal growth curve
Stages in the normal growth curve
 
Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.
 
An introduction on sequence tagged site mapping
An introduction on sequence tagged site mappingAn introduction on sequence tagged site mapping
An introduction on sequence tagged site mapping
 
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxPSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
 
COMPUTING ANTI-DERIVATIVES (Integration by SUBSTITUTION)
COMPUTING ANTI-DERIVATIVES(Integration by SUBSTITUTION)COMPUTING ANTI-DERIVATIVES(Integration by SUBSTITUTION)
COMPUTING ANTI-DERIVATIVES (Integration by SUBSTITUTION)
 
Introduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptxIntroduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptx
 
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICEPATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptx
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)
 
biology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGYbiology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGY
 
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)
 
Site Acceptance Test .
Site Acceptance Test                    .Site Acceptance Test                    .
Site Acceptance Test .
 
Velocity and Acceleration PowerPoint.ppt
Velocity and Acceleration PowerPoint.pptVelocity and Acceleration PowerPoint.ppt
Velocity and Acceleration PowerPoint.ppt
 

Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic Anonymity (ISMIR 2018)

  • 1. Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic Anonymity Kosetsu Tsukuda, Satoru Fukayama, Masataka Goto National Institute of Advanced Industrial Science and Technology (AIST), Japan Sept. 26, 2018
  • 2. I love music recommendation Music recommendation can improve user’s music experience
  • 3.  To improve recommendation accuracy, it is beneficial to predict user’s demographic attributes (age, gender, nationality)  A user’s demographics can be predicted with high accuracy by using the user’s play log 𝑡𝑡 Your nationality is Age Gender Nationality 4.13mean absolute error 77.01%accuracy 69.37%accuracy T. Krismayer, M. Schedl, P. Knees, R. Rabiser Prediction of User Demographics from Music Listening Habits CBMI 2017 Play log
  • 4. Technique to leverage play logs for predicting users' demographic attributes ? COUNTERBALANCE
  • 5. Technique to leverage play logs for predicting users' demographic attributes Technique to camouflage play logs for preserving users' demographic anonymity COUNTERBALANCE
  • 7. 𝑡𝑡  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 8. 𝑡𝑡 Listener Anonymizer … Compute a probability distribution  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 9. 𝑡𝑡 Listener Anonymizer Compute a probability distribution …  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 10. 𝑡𝑡 Listener Anonymizer Compute a probability distribution …  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 11. 𝑡𝑡 Listener Anonymizer Compute a probability distribution … …  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 12. 𝑡𝑡 Listener Anonymizer Compute a probability distribution … Listener Anonymizer Your nationality can be predicted as French with a probability of 67% Anonymize …  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 13. 𝑡𝑡 Listener Anonymizer Compute a probability distribution … … 0.21 0.04 0.77 0.89 0.48 0.92 0.25 0.33 0.82 0.29 0.46 0.86 𝑢𝑢1 𝑢𝑢2 𝑢𝑢𝑟𝑟 𝑠𝑠1 𝑠𝑠2 𝑠𝑠3 𝑠𝑠𝑚𝑚… … Compute the effectiveness of each song to anonymize her nationality 𝑢𝑢𝑖𝑖: user 𝑠𝑠𝑗𝑗: song  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 14. 𝑡𝑡 Listener Anonymizer Compute a probability distribution … … 0.21 0.04 0.77 0.89 0.48 0.92 0.25 0.33 0.82 0.29 0.46 0.86 𝑢𝑢1 𝑢𝑢2 𝑢𝑢𝑟𝑟 𝑠𝑠1 𝑠𝑠2 𝑠𝑠3 𝑠𝑠𝑚𝑚… … Compute the effectiveness of each song to anonymize her nationality Listener Anonymizer Recommendations: Play 𝑢𝑢𝑖𝑖: user 𝑠𝑠𝑗𝑗: song  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 15. 𝑡𝑡 Listener Anonymizer Compute a probability distribution … … 0.21 0.04 0.77 0.89 0.48 0.92 0.25 0.33 0.82 0.29 0.46 0.86 𝑢𝑢1 𝑢𝑢2 𝑢𝑢𝑟𝑟 𝑠𝑠1 𝑠𝑠2 𝑠𝑠3 𝑠𝑠𝑚𝑚… … Compute the effectiveness of each song to anonymize her nationality 𝑢𝑢𝑖𝑖: user 𝑠𝑠𝑗𝑗: song  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 16. … 𝑡𝑡 Listener Anonymizer Compute a probability distribution … 0.21 0.04 0.77 0.89 0.48 0.92 0.25 0.33 0.82 0.29 0.46 0.86 𝑢𝑢1 𝑢𝑢2 𝑢𝑢𝑟𝑟 𝑠𝑠1 𝑠𝑠2 𝑠𝑠3 𝑠𝑠𝑚𝑚… … Compute the effectiveness of each song to anonymize her nationality Your nationality is … ?? 𝑢𝑢𝑖𝑖: user 𝑠𝑠𝑗𝑗: song  Emma is a 22-year-old French female  She uses both an online music service and Listener Anonymizer  She concealed her nationality when she signed up to the service
  • 17. Age Gender Nationality 3.22songs 9.28songs 4.36songs 𝑡𝑡 … Avg number of songs for camouflaging play logs 30 songs
  • 18. Probability When a user plays 30 songs, the distribution is strongly biased to Polish (the left most graph)  She can camouflage her play log by playing only three songs recommended by Listener Anonymizer
  • 19. I can enjoy music while preserving my demographic anonymity! Without Listener Anonymizer With Listener Anonymizer  It is important to show that preserving users’ demographic anonymity is technically possible  Listener Anonymizer gives a choice to a user Demographic anonymity High rec. accuracy I do not care about my demographic anonymity!
  • 20.  Listener Anonymizer might degrade recommendation accuracy  We dared to propose this controversial approach to raise privacy issues in the ISMIR community