Geometric Algorithms for k-NN Poisoning

Authors

  • Diego Ihara Centurion University of Illinois at Chicago
  • Karine Chubarian University of Illinois at Chicago
  • Bohan Fan University of Illinois at Chicago
  • Francesco Sgherzi University of Illinois at Chicago
  • Thiruvenkadam Sivaprakasam Radhakrishnan University of Illinois at Chicago
  • Anastasios Sidiropoulos University of Illinois at Chicago
  • Angelo Straight University of Illinois at Chicago

DOI:

https://doi.org/10.57717/cgt.v4i2.55

Abstract

We propose a label poisoning attack on geometric data sets against k-nearest neighbor classification. We provide an algorithm that can compute an εn-additive approximation of the optimal poisoning in n 22^{O(d+k/\ε)} time for a given data set X in R⁠d, where |X| = n. Our algorithm achieves its objectives through the application of multi-scale random partitions.

Downloads

Published

2025-05-15

How to Cite

Ihara Centurion, D., Chubarian, K., Fan, B., Sgherzi, F., Sivaprakasam Radhakrishnan, T., Sidiropoulos, A., & Straight, A. (2025). Geometric Algorithms for k-NN Poisoning. Computing in Geometry and Topology, 4(2), 4:1–4:12. https://doi.org/10.57717/cgt.v4i2.55

Issue

Vol. 4 No. 2 (2025)

Section

Original Research Articles

Categories

License

Copyright (c) 2025 Diego Ihara Centurion, Karine Chubarian, Bohan Fan, Francesco Sgherzi, Thiruvenkadam Sivaprakasam Radhakrishnan, Anastasios Sidiropoulos, Angelo Straight

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).