Headless Horseman: Adversarial Attacks on Transfer Learning Models

Ahmed Abdelkader; Michael J. Curry; Liam Fowl; Tom Goldstein; Avi Schwarzschild; Manli Shu; Christoph Studer; Chen Zhu

ICASSP 2020accepted0 citations

Headless Horseman: Adversarial Attacks on Transfer Learning Models

Ahmed Abdelkader, Michael J. Curry, Liam Fowl, Tom Goldstein, Avi Schwarzschild, Manli Shu, Christoph Studer, Chen Zhu

Abstract

Transfer learning facilitates the training of task-specific classifiers using pre-trained models as feature extractors. We present a family of transferable adversarial attacks against such classifiers, generated without access to the classification head; we call these headless attacks. We first demonstrate successful transfer attacks against a victim network using only its feature extractor. This motivates the introduction of a label-blind adversarial attack. This transfer attack method does not require any information about the class-label space of the victim. Our attack lowers the accuracy of a ResNet18 trained on CIFAR10 by over 40%.

BibTeX

@inproceedings{icassp2020_headlesshorseman,
  title = {Headless Horseman: Adversarial Attacks on Transfer Learning Models},
  author = {Ahmed Abdelkader and Michael J. Curry and Liam Fowl and Tom Goldstein and Avi Schwarzschild and Manli Shu and Christoph Studer and Chen Zhu},
  booktitle = {ICASSP 2020},
  year = {2020}
}