English
Related papers

Related papers: Make Some Noise: Reliable and Efficient Single-Ste…

200 papers

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

Adversarial training is a cornerstone of robust deep learning, but fast methods like the Fast Gradient Sign Method (FGSM) often suffer from Catastrophic Overfitting (CO), where models become robust to single-step attacks but fail against…

Machine Learning · Computer Science 2026-05-19 Fares B. Mehouachi , Saif Eddin Jabari

PGD-based and FGSM-based are two popular adversarial training (AT) approaches for obtaining adversarially robust models. Compared with PGD-based AT, FGSM-based one is significantly faster but fails with catastrophic overfitting (CO). For…

Machine Learning · Computer Science 2022-10-06 Axi Niu , Kang Zhang , Chaoning Zhang , Chenshuang Zhang , In So Kweon , Chang D. Yoo , Yanning Zhang

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

A recent line of work focused on making adversarial training computationally efficient for deep learning models. In particular, Wong et al. (2020) showed that $\ell_\infty$-adversarial training with fast gradient sign method (FGSM) can fail…

Machine Learning · Computer Science 2020-10-27 Maksym Andriushchenko , Nicolas Flammarion

High cost of training time caused by multi-step adversarial example generation is a major challenge in adversarial training. Previous methods try to reduce the computational burden of adversarial training using single-step adversarial…

Machine Learning · Computer Science 2021-02-09 Lehui Xie , Yaopeng Wang , Jia-Li Yin , Ximeng Liu

Adversarial training is the most successful empirical method for increasing the robustness of neural networks against adversarial attacks. However, the most effective approaches, like training with Projected Gradient Descent (PGD) are…

Machine Learning · Computer Science 2020-03-18 Leo Schwinn , René Raab , Björn Eskofier

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

Making deep neural networks robust to small adversarial noises has recently been sought in many applications. Adversarial training through iterative projected gradient descent (PGD) has been established as one of the mainstream ideas to…

Machine Learning · Computer Science 2021-03-30 Zeinab Golgooni , Mehrdad Saberi , Masih Eskandar , Mohammad Hossein Rohban

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

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…

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

Single-step adversarial training (SSAT) has demonstrated the potential to achieve both efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a phenomenon that leads to a severely distorted classifier, making…

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

This paper studies fast adversarial training against sparse adversarial perturbations bounded by $l_0$ norm. We demonstrate the challenges of employing $1$-step attacks on $l_0$ bounded perturbations for fast adversarial training, including…

Machine Learning · Computer Science 2025-11-03 Xuyang Zhong , Yixiao Huang , Chen Liu

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

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

Fast adversarial training (FAT) is beneficial for improving the adversarial robustness of neural networks. However, previous FAT work has encountered a significant issue known as catastrophic overfitting when dealing with large perturbation…

Machine Learning · Computer Science 2023-08-25 Mengnan Zhao , Lihe Zhang , Yuqiu Kong , Baocai Yin
‹ Prev 1 2 3 10 Next ›