MLCRCVLGJul 26, 2018

Evaluating and Understanding the Robustness of Adversarial Logit Pairing

arXiv:1807.10272v2145 citations
Originality Synthesis-oriented
AI Analysis

This work identifies a critical vulnerability in a proposed defense for adversarial attacks, which is important for researchers and practitioners in machine learning security.

The paper evaluated the robustness of Adversarial Logit Pairing, a defense against adversarial examples, and found it achieved only 0.6% accuracy under the threat model it was designed for.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes