.png){kind=icon}
返回
Hard Adversarial Example Mining for Improving Robust Fairness
.png){kind=icon}
OA
AI
DOI：10.1109/TIFS.2024.3516554.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Adversarial training (AT) is widely considered the state-of-the-art technique for improving the robustness of deep neural networks (DNNs) against adversarial examples (AEs). Nevertheless, recent studies have revealed that adversarially trained models are prone to unfairness problems. Recent works in this field usually apply class-wise regularization methods to enhance the fairness of AT. However, this paper discovers that these paradigms can be sub-optimal in improving robust fairness. Specifically, we empirically observe that the AEs that are already robust (referred to as easy AEs in this paper) are useless and even harmful in improving robust fairness. To this end, we propose the hard adversarial example mining (HAM) technique which concentrates on mining hard AEs while discarding the easy AEs in AT. Specifically, HAM identifies the easy AEs and hard AEs with a fast adversarial attack method. By discarding the easy AEs and reweighting the hard AEs, the robust fairness of the model can be efficiently and effectively improved. Extensive experimental results on four image classification datasets demonstrate the improvement of HAM in robust fairness and training efficiency compared to several state-of-the-art fair adversarial training methods. Our code is available at https://github.com/yyl-github-1896/HAM.
Keyword:
Training
Robustness
Accuracy
Modeling
Optimization
Computational efficiency
Computational modeling
Sun
Perturbation methods
Entropy
Adversarial training
robust fairness
hard adversarial example mining
convolutional neural network
期刊
IF:
8
论文数:
5.3K
被引数:
2.3W
机构
引用论文
An Ultra‐sensitive, Rapidly Responsive Strain Sensor Based on Silver Microflakes by Simple Process
PREAI
分享收藏分享收藏
Comparative study of layer by layer assembled multilayer films based on graphene oxide and reduced graphene oxide on flexible polyurethane foam: flame retardant and smoke suppression properties.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏Generation of hydroxyl radicals by urban suspended particulate air matter. The role of iron ions城市悬浮颗粒物产生羟基自由基。铁离子的作用:
PREAI
分享收藏分享收藏
查看更多内容