.png){kind=icon}
返回
Robust long-tailed recognition with distribution-aware adversarial example generation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106932.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Confronting adversarial attacks and data imbalances, attaining adversarial robustness under long-tailed distribution presents a challenging problem. Adversarial training (AT) is a conventional solution for enhancing adversarial robustness, which generates adversarial examples (AEs) in a generation phase and subsequently trains on these AEs in a training phase. Existing long-tailed adversarial learning methods follow the AT framework and rebalance the AE classification in the training phase. However, few of them realize the impact of the long-tailed distribution on the generation phase. In this paper, we delve into the generation phase and uncover its imbalance across different classes. We evaluate the generation quality for different classes by comparing the differences between their generated AEs and natural examples. Our findings reveal that these differences are less pronounced in tail classes compared to head classes, indicating their inferior generation quality. To solve this problem, we propose the novel Distribution-Aware Adversarial Example Generation (DAG) method, which balances the AE generation for different classes using a Virtual Example Creator (VEC) and a Gradient-Guided Calibrator (GGC). The VEC creates virtual examples to introduce more adversarial perturbations for different classes, while the GGC calibrates the creation process to enhance the focus on tail classes based on their generation quality, effectively addressing the imbalance problem. Extensive experiments on three long-tailed adversarial benchmarks across five attack scenarios demonstrate DAG's effectiveness. On CIFAR-100-LT, DAG outperforms the previous RoBal by 4.0 points under the projected gradient descent (PGD) attack, highlighting its superiority in adversarial scenarios.
Keyword:
Long-tailed recognition
Adversarial robustness
Distribution-aware learning
Adversarial example generation
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
A systematic study of the class imbalance problem in convolutional neural networks卷积神经网络中类不平衡问题的系统研究.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏分享收藏Non-Circadian Expression Masking Clock-Driven Weak Transcription Rhythms in U2OS CellsPLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容