Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency

no code implementations • 25 May 2024 • Runqi Lin, Chaojian Yu, Bo Han, Hang Su, Tongliang Liu

Catastrophic overfitting (CO) presents a significant challenge in single-step adversarial training (AT), manifesting as highly distorted deep neural networks (DNNs) that are vulnerable to multi-step adversarial attacks.

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization

2 code implementations • NeurIPS 2023 • Runqi Lin, Chaojian Yu, Tongliang Liu

Specifically, we design a novel method, termed Abnormal Adversarial Examples Regularization (AAER), which explicitly regularizes the variation of AAEs to hinder the classifier from becoming distorted.

Adversarial Robustness

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting

1 code implementation • 13 Oct 2023 • Runqi Lin, Chaojian Yu, Bo Han, Tongliang Liu

In this work, we adopt a unified perspective by solely focusing on natural patterns to explore different types of overfitting.

Memorization