Adversarial learning

Statistics against Shayṭtān



Adversarial learning, where the noise is not purely random, but chosen to be the worst possible noise for you (subject to some rules of the game). This is in contrast to classic machine learning and statistics where the noise is purely random; Tyche is not “out to get you”.

As renewed in fame recently by the related (?) method of generative adversarial networks (although much older.)

The associated concept in normal human experience is Goodhardt’s law, which tells us that “people game the targets you set for them.”

🏗 discuss politics implied by treating the learning as a battle with a conniving adversary as opposed to an uncaringly random universe. I’m sure someone has done this well in a terribly eloquent blog post, but I haven’t found one I’d want to link to yet.

The toolset of adversarial techniques is broad. Game theory is an important one, but also computational complexity theory (how hard is to find adversarial inputs, or to learn despite them?) and lots of functional analysis and optimisation theory. Surely much other stuff I do not know because this is not really my field.

Applications are broad too — improving ML but also infosec, risk management etc.

Incoming

Adversarial attacks can be terrorism or freedom-fighting, depending on the pitch, natch: From data strikes to data poisoning, how consumers can take back control from corporations.

Tough love training

References

Abernethy, Jacob, Alekh Agarwal, Peter L Bartlett, and Alexander Rakhlin. 2009. A Stochastic View of Optimal Regret Through Minimax Duality.” arXiv:0903.5328 [Cs, Stat].
Abernethy, Jacob, Peter L Bartlett, and Elad Hazan. 2011. “Blackwell Approachability and No-Regret Learning Are Equivalent.” In, 20.
Arjovsky, Martin, and Léon Bottou. 2017. Towards Principled Methods for Training Generative Adversarial Networks.” arXiv:1701.04862 [Stat], January.
Arjovsky, Martin, Soumith Chintala, and Léon Bottou. 2017. Wasserstein Generative Adversarial Networks.” In International Conference on Machine Learning, 214–23.
Arora, Sanjeev, Rong Ge, Yingyu Liang, Tengyu Ma, and Yi Zhang. 2017. Generalization and Equilibrium in Generative Adversarial Nets (GANs).” arXiv:1703.00573 [Cs], March.
Bora, Ashish, Ajil Jalal, Eric Price, and Alexandros G. Dimakis. 2017. Compressed Sensing Using Generative Models.” In International Conference on Machine Learning, 537–46.
Bubeck, Sébastien, and Nicolò Cesa-Bianchi. 2012. Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Vol. 5. Boston: Now.
Bubeck, Sébastien, and Aleksandrs Slivkins. 2012. The Best of Both Worlds: Stochastic and Adversarial Bandits.” arXiv:1202.4473 [Cs], February.
Buckner, Cameron. 2020. Understanding Adversarial Examples Requires a Theory of Artefacts for Deep Learning.” Nature Machine Intelligence 2 (12): 731–36.
Gebhart, Thomas, Paul Schrater, and Alan Hylton. 2019. Characterizing the Shape of Activation Space in Deep Neural Networks.” arXiv:1901.09496 [Cs, Stat], January.
Ghosh, Arnab, Viveka Kulharia, Vinay Namboodiri, Philip H. S. Torr, and Puneet K. Dokania. 2017. Multi-Agent Diverse Generative Adversarial Networks.” arXiv:1704.02906 [Cs, Stat], April.
Goodfellow, Ian J., Jonathon Shlens, and Christian Szegedy. 2014. Explaining and Harnessing Adversarial Examples.” arXiv:1412.6572 [Cs, Stat], December.
Goodfellow, Ian, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets.” In Advances in Neural Information Processing Systems 27, edited by Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, 2672–80. NIPS’14. Cambridge, MA, USA: Curran Associates, Inc.
Grünwald, Peter D, and Joseph Y Halpern. 2007. A Game-Theoretic Analysis of Updating Sets of Probabilities.” Eprint arXiv:07113235.
Guo, Xin, Johnny Hong, Tianyi Lin, and Nan Yang. 2017. Relaxed Wasserstein with Applications to GANs.” arXiv:1705.07164 [Cs, Stat], May.
Ilyas, Andrew, Logan Engstrom, Shibani Santurkar, Brandon Tran, Dimitris Tsipras, and Aleksander Ma. 2019. “Adversarial Examples Are Not Bugs, They Are Features.” In Advances In Neural Information Processing Systems, 12.
Jetchev, Nikolay, Urs Bergmann, and Roland Vollgraf. 2016. Texture Synthesis with Spatial Generative Adversarial Networks.” In Advances in Neural Information Processing Systems 29.
Khim, Justin, Varun Jog, and Po-Ling Loh. 2016. Computationally Efficient Influence Maximization in Stochastic and Adversarial Models: Algorithms and Analysis.” arXiv:1611.00350 [Cs, Stat], November.
Larsen, Anders Boesen Lindbo, Søren Kaae Sønderby, Hugo Larochelle, and Ole Winther. 2015. Autoencoding Beyond Pixels Using a Learned Similarity Metric.” arXiv:1512.09300 [Cs, Stat], December.
Ohsawa, Shohei. 2021. Unbiased Self-Play.” arXiv:2106.03007 [Cs, Econ, Stat], June.
Poole, Ben, Alexander A. Alemi, Jascha Sohl-Dickstein, and Anelia Angelova. 2016. Improved Generator Objectives for GANs.” In Advances in Neural Information Processing Systems 29.
Radford, Alec, Luke Metz, and Soumith Chintala. 2015. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks.” In arXiv:1511.06434 [Cs].
Raghunathan, Arvind U., Anoop Cherian, and Devesh K. Jha. 2019. Game Theoretic Optimization via Gradient-Based Nikaido-Isoda Function.” arXiv:1905.05927 [Cs, Math, Stat], May.
Sato, Yuzuru, Eizo Akiyama, and J Doyne Farmer. 2002. Chaos in Learning a Simple Two-Person Game.” Proceedings of the National Academy of Sciences 99 (7): 4748–51.
Vervoort, Marco R. 1996. Blackwell Games.” In Statistics, Probability and Game Theory: Papers in Honor of David Blackwell, edited by T.S. Ferguson, L.S. Shapley, and J.B. MacQueen, 369–90. Institute of Mathematical Statistics.
Zhang, Rui, and Quanyan Zhu. 2017. Game-Theoretic Design of Secure and Resilient Distributed Support Vector Machines with Adversaries.” arXiv:1710.04677 [Cs, Stat], October.

No comments yet. Why not leave one?

GitHub-flavored Markdown & a sane subset of HTML is supported.