Abstract
As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference attack, an attacker has access to some data (called public data) of an individual, a software, or a system; and the attacker uses an ML classifier to automatically infer their private data. Inference attacks pose severe privacy and security threats to individuals and systems. Inference attacks are successful because private data are statistically correlated with public data, and ML classifiers can capture such statistical correlations. In this chapter, we discuss the opportunities and challenges of defending against ML-equipped inference attacks via adversarial examples. Our key observation is that attackers rely on ML classifiers in inference attacks. The adversarial machine learning community has demonstrated that ML classifiers have various vulnerabilities. Therefore, we can turn the vulnerabilities of ML into defenses against inference attacks. For example, ML classifiers are vulnerable to adversarial examples, which add carefully crafted noise to normal examples such that an ML classifier makes predictions for the examples as we desire. To defend against inference attacks, we can add carefully crafted noise into the public data to turn them into adversarial examples, such that attackers’ classifiers make incorrect predictions for the private data. However, existing methods to construct adversarial examples are insufficient because they did not consider the unique challenges and requirements for the crafted noise at defending against inference attacks. In this chapter, we take defending against inference attacks in online social networks as an example to illustrate the opportunities and challenges.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Code and dataset of AttriGuard are publicly available: https://github.com/jjy1994/AttriGuard.
- 2.
These attacks are also called attribute inference attacks [30]. To distinguish with attribute inference attacks in online social networks, we call them feature inference attacks.
References
Jahna Otterbacher. Inferring gender of movie reviewers: exploiting writing style, content and metadata. In CIKM, 2010.
Udi Weinsberg, Smriti Bhagat, Stratis Ioannidis, and Nina Taft. Blurme: Inferring and obfuscating user gender based on ratings. In RecSys, 2012.
E. Zheleva and L. Getoor. To join or not to join: The illusion of privacy in social networks with mixed public and private user profiles. In WWW, 2009.
Abdelberi Chaabane, Gergely Acs, and Mohamed Ali Kaafar. You are what you like! information leakage through users’ interests. In NDSS, 2012.
Michal Kosinski, David Stillwell, and Thore Graepel. Private traits and attributes are predictable from digital records of human behavior. PNAS, 2013.
Neil Zhenqiang Gong, Ameet Talwalkar, Lester Mackey, Ling Huang, Eui Chul Richard Shin, Emil Stefanov, Elaine(Runting) Shi, and Dawn Song. Joint link prediction and attribute inference using a social-attribute network. ACM TIST, 5(2), 2014.
Neil Zhenqiang Gong and Bin Liu. You are who you know and how you behave: Attribute inference attacks via users’ social friends and behaviors. In USENIX Security Symposium, 2016.
Jinyuan Jia, Binghui Wang, Le Zhang, and Neil Zhenqiang Gong. AttriInfer: Inferring user attributes in online social networks using markov random fields. In WWW, 2017.
Neil Zhenqiang Gong and Bin Liu. Attribute inference attacks in online social networks. ACM TOPS, 21(1), 2018.
Yang Zhang, Mathias Humbert, Tahleen Rahman, Cheng-Te Li, Jun Pang, and Michael Backes. Tagvisor: A privacy advisor for sharing hashtags. In WWW, 2018.
Arvind Narayanan, Hristo Paskov, Neil Zhenqiang Gong, John Bethencourt, Emil Stefanov, Eui Chul Richard Shin, and Dawn Song. On the feasibility of internet-scale author identification. In IEEE S&P, 2012.
Mathias Payer, Ling Huang, Neil Zhenqiang Gong, Kevin Borgolte, and Mario Frank. What you submit is who you are: A multi-modal approach for deanonymizing scientific publications. IEEE Transactions on Information Forensics and Security, 10(1), 2015.
Aylin Caliskan-Islam, Richard Harang, Andrew Liu, Arvind Narayanan, Clare Voss, Fabian Yamaguchi, and Rachel Greenstadt. De-anonymizing programmers via code stylometry. In USENIX Security Symposium, 2015.
Aylin Caliskan, Fabian Yamaguchi, Edwin Tauber, Richard Harang, Konrad Rieck, Rachel Greenstadt, and Arvind Narayanan. When coding style survives compilation: De-anonymizing programmers from executable binaries. In NDSS, 2018.
Rakshith Shetty, Bernt Schiele, and Mario Fritz. A4nt: Author attribute anonymity by adversarial training of neural machine translation. In USENIX Security Symposium, 2018.
Mohammed Abuhamad, Tamer AbuHmed, Aziz Mohaisen, and DaeHun Nyang. Large-scale and language-oblivious code authorship identification. In CCS, 2018.
Dominik Herrmann, Rolf Wendolsky, and Hannes Federrath. Website fingerprinting: attacking popular privacy enhancing technologies with the multinomial naĂŻve-bayes classifier. In ACM Workshop on Cloud Computing Security, 2009.
Andriy Panchenko, Lukas Niessen, Andreas Zinnen, and Thomas Engel. Website fingerprinting in onion routing based anonymization networks. In ACM workshop on Privacy in the Electronic Society, 2011.
Xiang Cai, Xin Cheng Zhang, Brijesh Joshi, and Rob Johnson. Touching from a distance: Website fingerprinting attacks and defenses. In CCS, 2012.
Marc Juarez, Sadia Afroz, Gunes Acar, Claudia Diaz, and Rachel Greenstadt. A critical evaluation of website fingerprinting attacks. In CCS, 2014.
Tao Wang, Xiang Cai, Rishab Nithyanand, Rob Johnson, and Ian Goldberg. Effective attacks and provable defenses for website fingerprinting. In USENIX Security Symposium, 2014.
Liran Lerman, Gianluca Bontempi, and Olivier Markowitch. Side channel attack: an approach based on machine learning. In COSADE, 2011.
Yinqian Zhang, Ari Juels, Michael K. Reiter, and Thomas Ristenpart. Cross-vm side channels and their use to extract private keys. In CCS, 2012.
Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. Membership Inference Attacks Against Machine Learning Models. In IEEE S&P, 2017.
Milad Nasr, Reza Shokri, and Amir Houmansadr. Machine Learning with Membership Privacy using Adversarial Regularization. In CCS, 2018.
Ahmed Salem, Yang Zhang, Mathias Humbert, Pascal Berrang, Mario Fritz, and Michael Backes. ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models. In NDSS, 2019.
Y. Michalevsky, G. Nakibly, A. Schulman, and D. Boneh. Powerspy: Location tracking using mobile device power analysis. In USENIX Security Symposium, 2015.
Sashank Narain, Triet D. Vo-Huu, Kenneth Block, and Guevara Noubir. Inferring user routes and locations using zero-permission mobile sensors. In IEEE S & P, 2016.
Matthew Fredrikson, Eric Lantz, Somesh Jha, Simon Lin, David Page, and Thomas Ristenpart. Privacy in pharmacogenetics: An end-to-end case study of personalized warfarin dosing. In USENIX Security Symposium, 2014.
S. Yeom, I. Giacomelli, M. Fredrikson, and S. Jha. Privacy risk in machine learning: Analyzing the connection to overfitting. In CSF, 2018.
Guixin Ye, Zhanyong Tang, Dingyi Fang, Zhanxing Zhu, Yansong Feng, Pengfei Xu, Xiaojiang Chen, and Zheng Wang. Yet another text captcha solver: A generative adversarial network based approach. In CCS, 2018.
Elie Bursztein, Romain Beauxis, Hristo Paskov, Daniele Perito, Celine Fabry, and John Mitchell. The failure of noise-based non-continuous audio captchas. In IEEE S & P, 2011.
Elie Bursztein, Matthieu Martin, and John C. Mitchell. Text-based captcha strengths and weaknesses. In CCS, 2011.
Cambridge Analytica. https://goo.gl/PqRjjX, May 2018.
Reza Shokri, George Theodorakopoulos, and Carmela Troncoso. Protecting location privacy: Optimal strategy against localization attacks. In CCS, 2012.
Reza Shokri. Privacy games: Optimal user-centric data obfuscation. In PETS, 2015.
Reza Shokri, George Theodorakopoulos, and Carmela Troncoso. Privacy games along location traces: A game-theoretic framework for optimizing location privacy. ACM TOPS, 19(4), 2016.
Nadia Fawaz Flávio du Pin Calmon. Privacy against statistical inference. In Allerton, 2012.
Jinyuan Jia and Neil Zhenqiang Gong. Attriguard: A practical defense against attribute inference attacks via adversarial machine learning. In USENIX Security Symposium, 2018.
Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. Calibrating noise to sensitivity in private data analysis. In TCC, 2006.
S. Warner. Randomized response: a survey technique for eliminating evasive answer bias. Journal of the American Statistical Association, 60(309), 1965.
J. C. Duchi, M. I. Jordan, and M. J. Wainwright. Local privacy and statistical minimax rates. In FOCS, 2013.
Aleksandra Korolova Ăšlfar Erlingsson, Vasyl Pihur. Rappor: Randomized aggregatable privacy-preserving ordinal response. In CCS, 2014.
R. Bassily and A. D. Smith. Local, private, efficient protocols for succinct histograms. In STOC, 2015.
Tianhao Wang, Jeremiah Blocki, Ninghui Li, and Somesh Jha. Locally differentially private protocols for frequency estimation. In USENIX Security Symposium, 2017.
Jinyuan Jia and Neil Zhenqiang Gong. Calibrate: Frequency estimation and heavy hitter identification with local differential privacy via incorporating prior knowledge. In INFOCOM, 2019.
Salman Salamatian, Amy Zhang, Flavio du Pin Calmon, Sandilya Bhamidipati, Nadia Fawaz, Branislav Kveton, Pedro Oliveira, and Nina Taft. Managing your private and public data: Bringing down inference attacks against your privacy. In IEEE Journal of Selected Topics in Signal Processing, 2015.
Marco Barreno, Blaine Nelson, Russell Sears, Anthony D Joseph, and J Doug Tygar. Can machine learning be secure? In ACM ASIACCS, 2006.
Battista Biggio, Igino Corona, Davide Maiorca, Blaine Nelson, Nedim ŚrndićPavel Laskov, Giorgio Giacinto, and Fabio Roli. Evasion attacks against machine learning at test time. In ECML-PKDD, 2013.
Jonathon Shlens Ian J. Goodfellow and Christian Szegedy. Explaining and harnessing adversarial examples. In ICLR, 2014.
Nicolas Papernot, Patrick McDaniel, Ian Goodfellow, Somesh Jha, Z Berkay Celik, and Ananthram Swami. Practical black-box attacks against machine learning. In AsiaCCS, 2017.
Yanpei Liu, Xinyun Chen, Chang Liu, and Dawn Song. Delving into transferable adversarial examples and black-box attacks. In ICLR, 2017.
Nicholas Carlini and David Wagner. Towards evaluating the robustness of neural networks. In IEEE S & P, 2017.
Nicolas Papernot, Patrick McDaniel, Somesh Jha, Matt Fredrikson, Z. Berkay Celik, and Ananthram Swami. The limitations of deep learning in adversarial settings. In EuroS&P, 2016.
Mahmood Sharif, Sruti Bhagavatula, Lujo Bauer, and K Michael Reiter. Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition. In CCS, 2016.
Convex Optimization. Cambridge University Press, 2004.
Neil Zhenqiang Gong, Wenchang Xu, Ling Huang, Prateek Mittal, Emil Stefanov, Vyas Sekar, and Dawn Song. Evolution of social-attribute networks: Measurements, modeling, and implications using google+. In IMC, 2012.
Chong Huang, Peter Kairouz, Xiao Chen, Lalitha Sankar, and Ram Rajagopal. Generative adversarial privacy. In Privacy in Machine Learning and Artificial Intelligence Workshop, 2018.
Terence Chen, Roksana Boreli, Mohamed-Ali Kaafar, and Arik Friedman. On the effectiveness of obfuscation techniques in online social networks. In PETS, 2014.
cvxpy. https://www.cvxpy.org/, June 2019.
Mehmet Sinan Inci, Thomas Eisenbarth, and Berk Sunar. Deepcloak: Adversarial crafting as a defensive measure to cloak processes. In arxiv, 2018.
Mohsen Imani, Mohammad Saidur Rahman, Nate Mathews, and Matthew Wright. Mockingbird: Defending against deep-learning-based website fingerprinting attacks with adversarial traces. In arxiv, 2019.
Xiaozhu Meng, Barton P Miller, and Somesh Jha. Adversarial binaries for authorship identification. In arxiv, 2018.
Erwin Quiring, Alwin Maier, and Konrad Rieck. Misleading authorship attribution of source code using adversarial learning. In USENIX Security Symposium, 2019.
Battista Biggio, Blaine Nelson, and Pavel Laskov. Poisoning attacks against support vector machines. In ICML, 2012.
Matthew Jagielski, Alina Oprea, Battista Biggio, Chang Liu, Cristina Nita-Rotaru, and Bo Li. Manipulating machine learning: Poisoning attacks and countermeasures for regression learning. In IEEE S & P, 2018.
Bo Li, Yining Wang, Aarti Singh, and Yevgeniy Vorobeychik. Data poisoning attacks on factorization-based collaborative filtering. In NIPS, 2016.
Guolei Yang, Neil Zhenqiang Gong, and Ying Cai. Fake co-visitation injection attacks to recommender systems. In NDSS, 2017.
Luis Muñoz-González, Battista Biggio, Ambra Demontis, Andrea Paudice, Vasin Wongrassamee, Emil C Lupu, and Fabio Roli. Towards poisoning of deep learning algorithms with back-gradient optimization. In AISec, 2017.
Ali Shafahi, W Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer, Tudor Dumitras, and Tom Goldstein. Poison frogs! targeted clean-label poisoning attacks on neural networks. In NeurIPS, 2018.
Octavian Suciu, Radu Marginean, Yigitcan Kaya, Hal Daume III, and Tudor Dumitras. When does machine learning fail? generalized transferability for evasion and poisoning attacks. In Usenix Security Symposium, 2018.
Minghong Fang, Guolei Yang, Neil Zhenqiang Gong, and Jia Liu. Poisoning attacks to graph-based recommender systems. In ACSAC, 2018.
H. Yu, M. Kaminsky, P. B. Gibbons, and A. Flaxman. SybilGuard: Defending against Sybil attacks via social networks. In SIGCOMM, 2006.
Qiang Cao, Michael Sirivianos, Xiaowei Yang, and Tiago Pregueiro. Aiding the detection of fake accounts in large scale social online services. In NSDI, 2012.
Gang Wang, Tristan Konolige, Christo Wilson, and Xiao Wang. You are how you click: Clickstream analysis for sybil detection. In Usenix Security Symposium, 2013.
Neil Zhenqiang Gong, Mario Frank, and Prateek Mittal. Sybilbelief: A semi-supervised learning approach for structure-based sybil detection. IEEE Transactions on Information Forensics and Security, 9(6):976–987, 2014.
Binghui Wang, Le Zhang, and Neil Zhenqiang Gong. Sybilscar: Sybil detection in online social networks via local rule based propagation. In INFOCOM, 2017.
Binghui Wang, Neil Zhenqiang Gong, and Hao Fu. Gang: Detecting fraudulent users in online social networks via guilt-by-association on directed graphs. In ICDM, 2017.
Peng Gao, Binghui Wang, Neil Zhenqiang Gong, Sanjeev R. Kulkarni, Kurt Thomas, and Prateek Mittal. Sybilfuse: Combining local attributes with global structure to perform robust sybil detection. In CNS, 2018.
Binghui Wang, Le Zhang, and Neil Zhenqiang Gong. Sybilblind: Detecting fake users in online social networks without manual labels. In RAID, 2018.
Binghui Wang, Jinyuan Jia, and Neil Zhenqiang Gong. Graph-based security and privacy analytics via collective classification with joint weight learning and propagation. In NDSS, 2019.
Zenghua Xia, Chang Liu, Neil Zhenqiang Gong, Qi Li, Yong Cui, and Dawn Song. Characterizing and detecting malicious accounts in privacy-centric mobile social networks: A case study. In KDD, 2019.
Jan Hendrik Metzen, Tim Genewein, Volker Fischer, and Bastian Bischof. On detecting adversarial perturbations. In ICLR, 2017.
Weilin Xu, David Evans, and Yanjun Qi. Feature squeezing: Detecting adversarial examples in deep neural networks. In NDSS, 2018.
Dongyu Meng and Hao Chen. Magnet: a two-pronged defense against adversarial examples. In CCS, 2017.
Warren He, Bo Li, and Dawn Song. Decision boundary analysis of adversarial examples. In ICLR, 2018.
Nicolas Papernot, Patrick McDaniel, Xi Wu, Somesh Jha, and Ananthram Swami. Distillation as a defense to adversarial perturbations against deep neural networks. In IEEE S & P, 2016.
Xiaoyu Cao and Neil Zhenqiang Gong. Mitigating evasion attacks to deep neural networks via region-based classification. In ACSAC, 2017.
Mathias Lecuyer, Vaggelis Atlidakis, Roxana Geambasu, Daniel Hsu, and Suman Jana. Certified robustness to adversarial examples with differential privacy. In IEEE S & P, 2019.
Jeremy M Cohen, Elan Rosenfeld, and J. Zico Kolter. Certified adversarial robustness via randomized smoothing. In ICML, 2019.
Shiqi Wang, Yizheng Chen, Ahmed Abdou, and Suman Jana. Mixtrain: Scalable training of verifiably robust neural networks. In arxiv, 2018.
Acknowledgement
This work was supported by NSF grant No. 1801584.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Jia, J., Gong, N.Z. (2020). Defending Against Machine Learning Based Inference Attacks via Adversarial Examples: Opportunities and Challenges. In: Jajodia, S., Cybenko, G., Subrahmanian, V., Swarup, V., Wang, C., Wellman, M. (eds) Adaptive Autonomous Secure Cyber Systems. Springer, Cham. https://doi.org/10.1007/978-3-030-33432-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-33432-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33431-4
Online ISBN: 978-3-030-33432-1
eBook Packages: Computer ScienceComputer Science (R0)