Fair Adversarial Training by Identifying and Augmenting Hard Examples
en-GBde-DEes-ESfr-FR

Fair Adversarial Training by Identifying and Augmenting Hard Examples

28/03/2025 Frontiers Journals

Adversarial training has been widely acknowledged as the most effective defense against adversarial attacks. However, recent research has demonstrated that a large discrepancy exists in the class-wise robustness of adversarial training, which could cause two potential issues: 1) buckets effect, where the least robust class can be exploited as a serious loophole, and 2) ethical issues, where some groups are protected with lower robustness. Therefore, unfair robustness is a critical issue that can severely hinder the practical application of adversarial training.

To address this challenge, a research team led by Qian Wang published their new research on 15 Mar 2025 in Frontiers of Computer Science co-published by Higher Education Press and Springer Nature.

The team proposed a novel fair adversarial training algorithm (FairAT), which aims to improve the robustness of hard classes and can be treated as an improvement of vanilla adversarial training. The proposed FairAT leverages the discovery that the uncertainty of robust models about examples is highly consistent with the class-wise robustness, which is used as a more fine-grained indicator of robust fairness. By dynamically augmenting hard examples throughout the training process, it outperforms state-of-the-art methods in terms of both overall robustness and fairness.

Future work can focus on designing more advanced methods to boost fairness, reducing the training cost of FairAT, and extending existing methods to other important tasks and modalities.

DOI: 10.1007/s11704-024-3587-1

Reference: Ningping MOU, Xinli YUE, Lingchen ZHAO, Qian WANG. Fairness is essential for robustness: fair adversarial training by identifying and augmenting hard examples. Front. Comput. Sci., 2025, 19(3): 193803 , https://doi.org/10.1007/s11704-024-3587-1
Archivos adjuntos
  • The training process of FairAT
28/03/2025 Frontiers Journals
Regions: Asia, China
Keywords: Applied science, Computing, Engineering

Disclaimer: AlphaGalileo is not responsible for the accuracy of content posted to AlphaGalileo by contributing institutions or for the use of any information through the AlphaGalileo system.

Testimonios

We have used AlphaGalileo since its foundation but frankly we need it more than ever now to ensure our research news is heard across Europe, Asia and North America. As one of the UK’s leading research universities we want to continue to work with other outstanding researchers in Europe. AlphaGalileo helps us to continue to bring our research story to them and the rest of the world.
Peter Dunn, Director of Press and Media Relations at the University of Warwick
AlphaGalileo has helped us more than double our reach at SciDev.Net. The service has enabled our journalists around the world to reach the mainstream media with articles about the impact of science on people in low- and middle-income countries, leading to big increases in the number of SciDev.Net articles that have been republished.
Ben Deighton, SciDevNet
AlphaGalileo is a great source of global research news. I use it regularly.
Robert Lee Hotz, LA Times

Trabajamos en estrecha colaboración con...


  • BBC
  • The Times
  • National Geographic
  • University of Cambridge
  • iesResearch
Copyright 2025 by DNN Corp Terms Of Use Privacy Statement