English
Related papers

Related papers: Eliminating Catastrophic Overfitting Via Abnormal …

200 papers

Adversarial training (AT) is the de facto method for building robust neural networks, but it can be computationally expensive. To mitigate this, fast single-step attacks can be used, but this may lead to catastrophic overfitting (CO). This…

Fast Adversarial Training (FAT) has gained increasing attention within the research community owing to its efficacy in improving adversarial robustness. Particularly noteworthy is the challenge posed by catastrophic overfitting (CO) in this…

Machine Learning · Computer Science 2024-02-29 Mengnan Zhao , Lihe Zhang , Yuqiu Kong , Baocai Yin

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves…

Machine Learning · Computer Science 2024-02-29 Elias Abad Rocamora , Fanghui Liu , Grigorios G. Chrysos , Pablo M. Olmos , Volkan Cevher

Adversarial training (AT) has become an effective defense method against adversarial examples (AEs) and it is typically framed as a bi-level optimization problem. Among various AT methods, fast AT (FAT), which employs a single-step attack…

Machine Learning · Computer Science 2024-07-18 Zhaoxin Wang , Handing Wang , Cong Tian , Yaochu Jin

Fast Adversarial Training (FAT) has attracted significant attention due to its efficiency in enhancing neural network robustness against adversarial attacks. However, FAT is prone to catastrophic overfitting (CO), wherein models overfit to…

Machine Learning · Computer Science 2026-04-28 Mengnan Zhao , Lihe Zhang , Tianhang Zheng , Bo Wang , Baocai Yin

Although fast adversarial training provides an efficient approach for building robust networks, it may suffer from a serious problem known as catastrophic overfitting (CO), where multi-step robust accuracy suddenly collapses to zero. In…

Machine Learning · Computer Science 2023-03-27 Zhengbao He , Tao Li , Sizhe Chen , Xiaolin Huang

Catastrophic overfitting (CO) presents a significant challenge in single-step adversarial training (AT), manifesting as highly distorted deep neural networks (DNNs) that are vulnerable to multi-step adversarial attacks. However, the…

Machine Learning · Computer Science 2024-09-17 Runqi Lin , Chaojian Yu , Bo Han , Hang Su , Tongliang Liu

Recently, Wong et al. showed that adversarial training with single-step FGSM leads to a characteristic failure mode named Catastrophic Overfitting (CO), in which a model becomes suddenly vulnerable to multi-step attacks. Experimentally they…

Machine Learning · Computer Science 2022-10-19 Pau de Jorge , Adel Bibi , Riccardo Volpi , Amartya Sanyal , Philip H. S. Torr , Grégory Rogez , Puneet K. Dokania

Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robust accuracy against adversarial attacks suddenly and…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Xiaojun Jia , Yong Zhang , Xingxing Wei , Baoyuan Wu , Ke Ma , Jue Wang , Xiaochun Cao

While adversarial training is an effective defense method against adversarial attacks, it notably increases the training cost. To this end, fast adversarial training (FAT) is presented for efficient training and has become a hot research…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Jie Gui , Chengze Jiang , Minjing Dong , Kun Tong , Xinli Shi , Yuan Yan Tang , Dacheng Tao

There has been a recent surge in single-step adversarial training as it shows robustness and efficiency. However, a phenomenon referred to as ``catastrophic overfitting" has been observed, which is prevalent in single-step defenses and may…

Machine Learning · Computer Science 2022-10-12 Zhuorong Li , Daiwei Yu

Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often suffers from Catastrophic Overfitting (CO), which results…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Xiaojun Jia , Yuefeng Chen , Xiaofeng Mao , Ranjie Duan , Jindong Gu , Rong Zhang , Hui Xue , Xiaochun Cao

In the field of adversarial robustness, there is a common practice that adopts the single-step adversarial training for quickly developing adversarially robust models. However, the single-step adversarial training is most likely to cause…

Machine Learning · Computer Science 2021-06-30 Xiaosen Wang , Chuanbiao Song , Liwei Wang , Kun He

Recently, FGSM adversarial training is found to be able to train a robust model which is comparable to the one trained by PGD but an order of magnitude faster. However, there is a failure mode called catastrophic overfitting (CO) that the…

Machine Learning · Computer Science 2021-05-10 Peilin Kang , Seyed-Mohsen Moosavi-Dezfooli

We aim at using Energy-based Model (EBM) framework to better understand adversarial training (AT) in classifiers, and additionally to analyze the intrinsic generative capabilities of robust classifiers. By viewing standard classifiers…

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of…

Machine Learning · Computer Science 2022-06-07 Zhichao Huang , Yanbo Fan , Chen Liu , Weizhong Zhang , Yong Zhang , Mathieu Salzmann , Sabine Süsstrunk , Jue Wang

Although fast adversarial training has demonstrated both robustness and efficiency, the problem of "catastrophic overfitting" has been observed. This is a phenomenon in which, during single-step adversarial training, the robust accuracy…

Machine Learning · Computer Science 2020-12-16 Hoki Kim , Woojin Lee , Jaewook Lee

Adversarial training (AT) is widely considered as the most promising strategy to defend against adversarial attacks and has drawn increasing interest from researchers. However, the existing AT methods still suffer from two challenges.…

Machine Learning · Computer Science 2024-05-21 Lilin Zhang , Ning Yang , Yanchao Sun , Philip S. Yu

Ensemble Adversarial Training (EAT) attempts to enhance the robustness of models against adversarial attacks by leveraging multiple models. However, current EAT strategies tend to train the sub-models independently, ignoring the cooperative…

Machine Learning · Computer Science 2025-09-03 Li Dengjin , Guo Yanming , Xie Yuxiang , Li Zheng , Chen Jiangming , Li Xiaolong , Lao Mingrui

Despite the remarkable success achieved by deep learning algorithms in various domains, such as computer vision, they remain vulnerable to adversarial perturbations. Adversarial Training (AT) stands out as one of the most effective…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Mahdi Salmani , Alireza Dehghanpour Farashah , Mohammad Azizmalayeri , Mahdi Amiri , Navid Eslami , Mohammad Taghi Manzuri , Mohammad Hossein Rohban
‹ Prev 1 2 3 10 Next ›