Research map / Adversarial robustness and security / Certified and empirical robustness

A Simple Class-Agnostic Approach to Enhance Fair Adversarial Training

NeurIPS 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training refinements

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a simple class-agnostic approach to improve fair adversarial training, aiming to raise robustness of the worst-performing classes in adversarial training.

Problem

Adversarial training improves robustness but yields large class-wise robustness disparities; fair adversarial training seeks to boost the worst-performing classes.

Approach

A simple class-agnostic modification to fair adversarial training that avoids class-specific handling; details beyond the abstract are not stated in the provided text.

Experimental setup

Builds on: adversarial training

Closest papers by meaning

• DAFA: Distance-Aware Fair Adversarial Training (ICLR 2024 · similarity 0.91)
• Towards Fairness-Aware Adversarial Learning (CVPR 2024 · similarity 0.90)
• On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness (ICML 2025 · similarity 0.90)
• Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation (NeurIPS 2024 · similarity 0.89)
• Adversarial Training Should Be Cast as a Non-Zero-Sum Game (ICLR 2024 · similarity 0.89)
• Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.89)