English

Evaluating and Understanding the Robustness of Adversarial Logit Pairing

Machine Learning 2018-11-27 v2 Cryptography and Security Computer Vision and Pattern Recognition Machine Learning

Abstract

We evaluate the robustness of Adversarial Logit Pairing, a recently proposed defense against adversarial examples. We find that a network trained with Adversarial Logit Pairing achieves 0.6% accuracy in the threat model in which the defense is considered. We provide a brief overview of the defense and the threat models/claims considered, as well as a discussion of the methodology and results of our attack, which may offer insights into the reasons underlying the vulnerability of ALP to adversarial attack.

Keywords

Cite

@article{arxiv.1807.10272,
  title  = {Evaluating and Understanding the Robustness of Adversarial Logit Pairing},
  author = {Logan Engstrom and Andrew Ilyas and Anish Athalye},
  journal= {arXiv preprint arXiv:1807.10272},
  year   = {2018}
}

Comments

NeurIPS SECML 2018. Source code at https://github.com/labsix/adversarial-logit-pairing-analysis

R2 v1 2026-06-23T03:15:47.337Z