CFA: Class-wise Calibrated Fair Adversarial Training
- URL: http://arxiv.org/abs/2303.14460v1
- Date: Sat, 25 Mar 2023 13:05:16 GMT
- Title: CFA: Class-wise Calibrated Fair Adversarial Training
- Authors: Zeming Wei, Yifei Wang, Yiwen Guo, Yisen Wang
- Abstract summary: We propose a textbfClass-wise calibrated textbfFair textbfAdversarial training framework, named CFA, which customizes specific training configurations for each class automatically.
Our proposed CFA can improve both overall robustness and fairness notably over other state-of-the-art methods.
- Score: 31.812287233814295
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Adversarial training has been widely acknowledged as the most effective
method to improve the adversarial robustness against adversarial examples for
Deep Neural Networks (DNNs). So far, most existing works focus on enhancing the
overall model robustness, treating each class equally in both the training and
testing phases. Although revealing the disparity in robustness among classes,
few works try to make adversarial training fair at the class level without
sacrificing overall robustness. In this paper, we are the first to
theoretically and empirically investigate the preference of different classes
for adversarial configurations, including perturbation margin, regularization,
and weight averaging. Motivated by this, we further propose a
\textbf{C}lass-wise calibrated \textbf{F}air \textbf{A}dversarial training
framework, named CFA, which customizes specific training configurations for
each class automatically. Experiments on benchmark datasets demonstrate that
our proposed CFA can improve both overall robustness and fairness notably over
other state-of-the-art methods. Code is available at
\url{https://github.com/PKU-ML/CFA}.
Related papers
- Learning Fair Robustness via Domain Mixup [8.471466670802817]
We propose the use of mixup for the problem of learning fair robust classifiers.
We show that mixup combined with adversarial training can provably reduce the class-wise robustness disparity.
arXiv Detail & Related papers (2024-11-21T18:56:33Z) - Towards Fairness-Aware Adversarial Learning [13.932705960012846]
We propose a novel learning paradigm, named Fairness-Aware Adversarial Learning (FAAL)
Our method aims to find the worst distribution among different categories, and the solution is guaranteed to obtain the upper bound performance with high probability.
In particular, FAAL can fine-tune an unfair robust model to be fair within only two epochs, without compromising the overall clean and robust accuracies.
arXiv Detail & Related papers (2024-02-27T18:01:59Z) - Enhancing Compositional Generalization via Compositional Feature Alignment [14.289836081158615]
We develop CG-Bench, a suite of CG benchmarks derived from existing real-world image datasets.
We propose Compositional Feature Alignment (CFA), a simple two-stage finetuning technique.
We conduct experiments on CG-Bench for CLIP and DINOv2, two powerful pretrained vision foundation models.
arXiv Detail & Related papers (2024-02-05T10:06:24Z) - TWINS: A Fine-Tuning Framework for Improved Transferability of
Adversarial Robustness and Generalization [89.54947228958494]
This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks.
We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework.
TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
arXiv Detail & Related papers (2023-03-20T14:12:55Z) - Learning Sample Reweighting for Accuracy and Adversarial Robustness [15.591611864928659]
We propose a novel adversarial training framework that learns to reweight the loss associated with individual training samples based on a notion of class-conditioned margin.
Our approach consistently improves both clean and robust accuracy compared to related methods and state-of-the-art baselines.
arXiv Detail & Related papers (2022-10-20T18:25:11Z) - Improving Robust Fairness via Balance Adversarial Training [51.67643171193376]
Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes.
We propose Adversarial Training (BAT) to address the robust fairness problem.
arXiv Detail & Related papers (2022-09-15T14:44:48Z) - Distributed Adversarial Training to Robustify Deep Neural Networks at
Scale [100.19539096465101]
Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification.
To defend against such attacks, an effective approach, known as adversarial training (AT), has been shown to mitigate robust training.
We propose a large-batch adversarial training framework implemented over multiple machines.
arXiv Detail & Related papers (2022-06-13T15:39:43Z) - Enhancing Adversarial Training with Feature Separability [52.39305978984573]
We introduce a new concept of adversarial training graph (ATG) with which the proposed adversarial training with feature separability (ATFS) enables to boost the intra-class feature similarity and increase inter-class feature variance.
Through comprehensive experiments, we demonstrate that the proposed ATFS framework significantly improves both clean and robust performance.
arXiv Detail & Related papers (2022-05-02T04:04:23Z) - Sparsity Winning Twice: Better Robust Generalization from More Efficient
Training [94.92954973680914]
We introduce two alternatives for sparse adversarial training: (i) static sparsity and (ii) dynamic sparsity.
We find both methods to yield win-win: substantially shrinking the robust generalization gap and alleviating the robust overfitting.
Our approaches can be combined with existing regularizers, establishing new state-of-the-art results in adversarial training.
arXiv Detail & Related papers (2022-02-20T15:52:08Z) - Analysis and Applications of Class-wise Robustness in Adversarial
Training [92.08430396614273]
Adversarial training is one of the most effective approaches to improve model robustness against adversarial examples.
Previous works mainly focus on the overall robustness of the model, and the in-depth analysis on the role of each class involved in adversarial training is still missing.
We provide a detailed diagnosis of adversarial training on six benchmark datasets, i.e., MNIST, CIFAR-10, CIFAR-100, SVHN, STL-10 and ImageNet.
We observe that the stronger attack methods in adversarial learning achieve performance improvement mainly from a more successful attack on the vulnerable classes.
arXiv Detail & Related papers (2021-05-29T07:28:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.