English
Related papers

Related papers: Understanding Catastrophic Overfitting in Single-s…

200 papers

Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have…

Machine Learning · Computer Science 2022-11-28 Muhammad Zaid Hameed , Beat Buesser

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

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

Machine Learning · Computer Science 2020-06-08 Bai Li , Shiqi Wang , Suman Jana , Lawrence Carin

Adversarial Training (AT) with Projected Gradient Descent (PGD) is an effective approach for improving the robustness of the deep neural networks. However, PGD AT has been shown to suffer from two main limitations: i) high computational…

Computer Vision and Pattern Recognition · Computer Science 2020-12-29 Ahmadreza Jeddi , Mohammad Javad Shafiee , Alexander Wong

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

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

Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique that approximately solves a robust optimization problem to minimize the worst-case loss and is widely…

Machine Learning · Computer Science 2022-03-28 Theodoros Tsiligkaridis , Jay Roberts

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

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

Adversarial training suffers from the issue of robust overfitting, which seriously impairs its generalization performance. Data augmentation, which is effective at preventing overfitting in standard training, has been observed by many…

Computer Vision and Pattern Recognition · Computer Science 2023-01-25 Lin Li , Michael Spratling

It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically, that such practices surprisingly do not unduly harm the…

Machine Learning · Computer Science 2020-03-05 Leslie Rice , Eric Wong , J. Zico Kolter

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

This paper examines the phenomenon of probabilistic robustness overestimation in TRADES, a prominent adversarial training method. Our study reveals that TRADES sometimes yields disproportionately high PGD validation accuracy compared to the…

Machine Learning · Computer Science 2024-10-11 Jonathan Weiping Li , Ren-Wei Liang , Cheng-Han Yeh , Cheng-Chang Tsai , Kuanchun Yu , Chun-Shien Lu , Shang-Tse Chen

In recent years, deep neural networks have demonstrated outstanding performance in many machine learning tasks. However, researchers have discovered that these state-of-the-art models are vulnerable to adversarial examples: legitimate…

Machine Learning · Computer Science 2018-10-10 Ting-Jui Chang , Yukun He , Peng Li

Adversarial training has shown promise in building robust models against adversarial examples. A major drawback of adversarial training is the computational overhead introduced by the generation of adversarial examples. To overcome this…

Computer Vision and Pattern Recognition · Computer Science 2023-10-25 Xiaojun Jia , Jianshu Li , Jindong Gu , Yang Bai , Xiaochun Cao

In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon is called robust overfitting, and it can be observed when…

Machine Learning · Computer Science 2022-11-01 Jiancong Xiao , Yanbo Fan , Ruoyu Sun , Jue Wang , Zhi-Quan Luo

Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite contributing…

Machine Learning · Computer Science 2025-12-29 Youran Ye , Dejin Wang , Ajinkya Bhandare

Adversarial training, a method for learning robust deep networks, is typically assumed to be more expensive than traditional training due to the necessity of constructing adversarial examples via a first-order method like projected gradient…

Machine Learning · Computer Science 2020-01-14 Eric Wong , Leslie Rice , J. Zico Kolter

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

Adversarial training is a popular method to robustify models against adversarial attacks. However, it exhibits much more severe overfitting than training on clean inputs. In this work, we investigate this phenomenon from the perspective of…

Machine Learning · Computer Science 2024-12-18 Chen Liu , Zhichao Huang , Mathieu Salzmann , Tong Zhang , Sabine Süsstrunk