ICML 2021spotlight53 citations

Model-Targeted Poisoning Attacks with Provable Convergence

Fnu Suya, Saeed Mahloujifar, Anshuman Suri, David Evans, Yuan Tian

Abstract

In a poisoning attack, an adversary who controls a small fraction of the training data attempts to select that data, so a model is induced that misbehaves in a particular way. We consider poisoning attacks against convex machine learning models and propose an efficient poisoning attack designed to induce a model specified by the adversary. Unlike previous model-targeted poisoning attacks, our attack comes with provable convergence to any attainable target model. We also provide a lower bound on the minimum number of poisoning points needed to achieve a given target model. Our method uses online convex optimization and finds poisoning points incrementally. This provides more flexibility than previous attacks which require an a priori assumption about the number of poisoning points. Our attack is the first model-targeted poisoning attack that provides provable convergence for convex models. In our experiments, it either exceeds or matches state-of-the-art attacks in terms of attack success rate and distance to the target model.

BibTeX
@InProceedings{pmlr-v139-suya21a,
  title = 	 {Model-Targeted Poisoning Attacks with Provable Convergence},
  author =       {Suya, Fnu and Mahloujifar, Saeed and Suri, Anshuman and Evans, David and Tian, Yuan},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {10000--10010},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/suya21a/suya21a.pdf},
  url = 	 {https://proceedings.mlr.press/v139/suya21a.html},
  abstract = 	 {In a poisoning attack, an adversary who controls a small fraction of the training data attempts to select that data, so a model is induced that misbehaves in a particular way. We consider poisoning attacks against convex machine learning models and propose an efficient poisoning attack designed to induce a model specified by the adversary. Unlike previous model-targeted poisoning attacks, our attack comes with provable convergence to any attainable target model. We also provide a lower bound on the minimum number of poisoning points needed to achieve a given target model. Our method uses online convex optimization and finds poisoning points incrementally. This provides more flexibility than previous attacks which require an a priori assumption about the number of poisoning points. Our attack is the first model-targeted poisoning attack that provides provable convergence for convex models. In our experiments, it either exceeds or matches state-of-the-art attacks in terms of attack success rate and distance to the target model.}
}
Model-Targeted Poisoning Attacks with Provable Convergence · ICML 2021