Adversarial Examples Make Strong PoisonsDownload PDF

May 21, 2021 (edited Oct 26, 2021)NeurIPS 2021 PosterReaders: Everyone
  • Keywords: Data Poisoning, Robustness, Security, Adversarial Examples, Data Release, Availability Attack
  • TL;DR: We find that adversarial examples make stronger availability poisons than other methods designed specifically for data poisoning.
  • Abstract: The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained models, are even more effective for data poisoning than recent methods designed specifically for poisoning. In fact, adversarial examples with labels re-assigned by the crafting network remain effective for training, suggesting that adversarial examples contain useful semantic content, just with the "wrong" labels (according to a network, but not a human). Our method, adversarial poisoning, is substantially more effective than existing poisoning methods for secure dataset release, and we release a poisoned version of ImageNet, ImageNet-P, to encourage research into the strength of this form of data obfuscation.
  • Supplementary Material: pdf
  • Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
  • Code: https://github.com/lhfowl/adversarial_poisons
18 Replies

Loading