On Robustness of Linear Classifiers to Targeted Data Poisoning

Nakshatra Gupta; Sumanth Prabhu S; Supratik Chakraborty; Venkatesh R

AAAI 2026technical0 citations

On Robustness of Linear Classifiers to Targeted Data Poisoning

Nakshatra Gupta, Sumanth Prabhu S, Supratik Chakraborty, Venkatesh R

Abstract

Data poisoning is a training-time attack that undermines the trustworthiness of learned models. In a targeted data poisoning attack, an adversary manipulates the training dataset to alter the classification of a targeted test point. Given the typically large size of training dataset, manual detection of poisoning is difficult. An alternative is to automatically measure a dataset

BibTeX

@inproceedings{aaai2026_onrobustnessofli,
  title = {On Robustness of Linear Classifiers to Targeted Data Poisoning},
  author = {Nakshatra Gupta and Sumanth Prabhu S and Supratik Chakraborty and Venkatesh R},
  booktitle = {AAAI 2026},
  year = {2026}
}