2000 character limit reached
Geometric Algorithms for $k$-NN Poisoning (2306.12377v1)
Published 21 Jun 2023 in cs.LG, cs.CG, and cs.CR
Abstract: We propose a label poisoning attack on geometric data sets against $k$-nearest neighbor classification. We provide an algorithm that can compute an $\varepsilon n$-additive approximation of the optimal poisoning in $n\cdot 2{2{O(d+k/\varepsilon)}}$ time for a given data set $X \in \mathbb{R}d$, where $|X| = n$. Our algorithm achieves its objectives through the application of multi-scale random partitions.
- Recent advances in adversarial training for adversarial robustness. In Z. Zhou, editor, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021, pages 4312–4321. ijcai.org, 2021.
- B. Biggio and F. Roli. Wild patterns: Ten years after the rise of adversarial machine learning. Pattern Recognit., 84:317–331, 2018.
- N. Carlini. Poisoning the unlabeled dataset of semi-supervised learning. In M. Bailey and R. Greenstadt, editors, 30th USENIX Security Symposium, USENIX Security 2021, August 11-13, 2021, pages 1577–1592. USENIX Association, 2021.
- Approximating a finite metric by a small number of tree metrics. In Proceedings 39th Annual Symposium on Foundations of Computer Science (Cat. No. 98CB36280), pages 379–388. IEEE, 1998.
- Suspicion-free adversarial attacks on clustering algorithms. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, New York, February 7-12, 2020, pages 3625–3632. AAAI Press, 2020.
- Fairness degrading adversarial attacks against clustering algorithms. CoRR, abs/2110.12020, 2021.
- A black-box adversarial attack for poisoning clustering. Pattern Recognition, 122:108306, 2022.
- E. Fix and J. L. Hodges. Discriminatory analysis. nonparametric discrimination: Consistency properties. International Statistical Review/Revue Internationale de Statistique, 57(3):238–247, 1989.
- Explaining and harnessing adversarial examples. In International Conference on Learning Representations, 2015.
- Multilayer feedforward networks are universal approximators. Neural Networks, 2(5):359–366, 1989.
- Adversarial machine learning. In Proceedings of the 4th ACM workshop on Security and artificial intelligence, pages 43–58, 2011.
- Certified robustness of nearest neighbors against data poisoning attacks. CoRR, abs/2012.03765, 2020.
- J. R. Lee and A. Naor. Extending lipschitz functions via random metric partitions. Inventiones mathematicae, 160(1):59–95, 2005.
- J. R. Lee and A. Sidiropoulos. On the geometry of graphs with a forbidden minor. In Proceedings of the forty-first annual ACM symposium on Theory of computing, pages 245–254, 2009.
- Towards deep learning models resistant to adversarial attacks, 2019.
- Label sanitization against label flipping poisoning attacks. In Joint European conference on machine learning and knowledge discovery in databases, pages 5–15. Springer, 2018.
- A taxonomy and survey of attacks against machine learning. Comput. Sci. Rev., 34, 2019.
- Certified robustness to label-flipping attacks via randomized smoothing. In International Conference on Machine Learning, pages 8230–8241. PMLR, 2020.
- A system-driven taxonomy of attacks and defenses in adversarial machine learning. IEEE Trans. Emerg. Top. Comput. Intell., 4(4):450–467, 2020.
- Efficient label contamination attacks against black-box learning models. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, pages 3945–3951, 2017.