Geometric Algorithms for k-NN Poisoning
Not on the map. Why?
Abstract (arXiv)
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· 2^2O(d+k/varepsilon) time for a given data set X ∈ ℝd, where |X| = n. Our algorithm achieves its objectives through the application of multi-scale random partitions.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 23 references that are in the map. First posted on arXiv 21 Jun 2023.
Builds on
11 of 23 references.
References · 11
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
- 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
- 2020Certified Robustness to Label-Flipping Attacks via Randomized Smoothingcited by 108
- 2018Label Sanitization against Label Flipping Poisoning Attackscited by 73
- 2020Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attackscited by 60
- 2021Poisoning the Unlabeled Dataset of Semi-Supervised Learningcited by 44
- 2020A black-box adversarial attack for poisoning clusteringcited by 16
- 2019Suspicion-Free Adversarial Attacks on Clustering Algorithmscited by 11
- 2021Fairness Degrading Adversarial Attacks Against Clustering Algorithmscited by 5
Built on by
Not cited yet.