Evaluating and Understanding the Robustness of Adversarial Logit Pairing

July 26, 2018 · Entered Twilight · 🏛 arXiv.org

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, datasets, examples.png, model_lib.py, robustml_attack.py, robustml_eval.py, robustml_model.py

Authors Logan Engstrom, Andrew Ilyas, Anish Athalye arXiv ID 1807.10272 Category stat.ML: Machine Learning (Stat) Cross-listed cs.CR, cs.CV, cs.LG Citations 145 Venue arXiv.org Repository https://github.com/labsix/adversarial-logit-pairing-analysis ⭐ 60 Last Checked 1 month ago

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.