中文
相关论文

相关论文: Revisiting the Relationship between Adversarial an…

200 篇论文

Adversarial training (AT) has proven to be one of the most effective ways to defend Deep Neural Networks (DNNs) against adversarial attacks. However, the phenomenon of robust overfitting, i.e., the robustness will drop sharply at a certain…

机器学习 · 计算机科学 2022-05-25 Shudong Zhang , Haichang Gao , Tianwei Zhang , Yunyi Zhou , Zihui Wu

Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and generalization in adversarially trained models involves a…

计算与语言 · 计算机科学 2023-12-12 Enes Altinisik , Hassan Sajjad , Husrev Taha Sencar , Safa Messaoud , Sanjay Chawla

While adversarial training can improve robust accuracy (against an adversary), it sometimes hurts standard accuracy (when there is no adversary). Previous work has studied this tradeoff between standard and robust accuracy, but only in the…

机器学习 · 计算机科学 2019-08-28 Aditi Raghunathan , Sang Michael Xie , Fanny Yang , John C. Duchi , Percy Liang

By injecting adversarial examples into training data, adversarial training is promising for improving the robustness of deep learning models. However, most existing adversarial training approaches are based on a specific type of adversarial…

机器学习 · 计算机科学 2019-03-18 Chuanbiao Song , Kun He , Liwei Wang , John E. Hopcroft

Deep learning has achieved great success in computer vision, but remains vulnerable to adversarial attacks. Adversarial training is the leading defense designed to improve model robustness. However, its effect on the transferability of…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Mohamed Awad , Mahmoud Akrm , Walid Gomaa

Adversarial training (AT) has been demonstrated as one of the most promising defense methods against various adversarial attacks. To our knowledge, existing AT-based methods usually train with the locally most adversarial perturbed points…

计算机视觉与模式识别 · 计算机科学 2021-09-07 Chuanbiao Song , Yanbo Fan , Yichen Yang , Baoyuan Wu , Yiming Li , Zhifeng Li , Kun He

Deep neural networks are susceptible to adversarial attacks and common corruptions, which undermine their robustness. In order to enhance model resilience against such challenges, Adversarial Training (AT) has emerged as a prominent…

机器学习 · 计算机科学 2025-06-17 Tejaswini Medi , Steffen Jung , Margret Keuper

Adversarial training (AT) is a popular method for training robust deep neural networks (DNNs) against adversarial attacks. Yet, AT suffers from two shortcomings: (i) the robustness of DNNs trained by AT is highly intertwined with the size…

机器学习 · 计算机科学 2024-05-24 Shayan Mohajer Hamidi , Linfeng Ye

Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most…

机器学习 · 计算机科学 2023-07-17 Olukorede Fakorede , Ashutosh Kumar Nirala , Modeste Atsague , Jin Tian

Adversarial training is one of the main defenses against adversarial attacks. In this paper, we provide the first rigorous study on diagnosing elements of adversarial training, which reveals two intriguing properties. First, we study the…

计算机视觉与模式识别 · 计算机科学 2019-12-24 Cihang Xie , Alan Yuille

To advance the understanding of robust deep learning, we delve into the effects of adversarial training on self-supervised and supervised contrastive learning alongside supervised learning. Our analysis uncovers significant disparities…

机器学习 · 计算机科学 2023-06-08 Fatemeh Ghofrani , Mehdi Yaghouti , Pooyan Jamshidi

Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization…

机器学习 · 计算机科学 2022-12-21 Zhiyuan Zhang , Wei Li , Ruihan Bao , Keiko Harimoto , Yunfang Wu , Xu Sun

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

计算机视觉与模式识别 · 计算机科学 2021-09-08 Omid Poursaeed , Tianxing Jiang , Harry Yang , Serge Belongie , SerNam Lim

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…

机器学习 · 计算机科学 2022-11-28 Muhammad Zaid Hameed , Beat Buesser

Despite the rapid progress of neural networks, they remain highly vulnerable to adversarial examples, for which adversarial training (AT) is currently the most effective defense. While AT has been extensively studied, its practical…

机器学习 · 计算机科学 2025-10-16 Yisen Wang , Yichuan Mo , Hongjun Wang , Junyi Li , Zhouchen Lin

Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the robust fairness problem. Previously proposed Fair Robust…

机器学习 · 计算机科学 2022-09-19 Chunyu Sun , Chenye Xu , Chengyuan Yao , Siyuan Liang , Yichao Wu , Ding Liang , XiangLong Liu , Aishan Liu

Machine learning classifiers with high test accuracy often perform poorly under adversarial attacks. It is commonly believed that adversarial training alleviates this issue. In this paper, we demonstrate that, surprisingly, the opposite may…

机器学习 · 计算机科学 2022-03-30 Jacob Clarysse , Julia Hörrmann , Fanny Yang

The deep neural networks are known to be vulnerable to well-designed adversarial attacks. The most successful defense technique based on adversarial training (AT) can achieve optimal robustness against particular attacks but cannot…

计算机视觉与模式识别 · 计算机科学 2024-08-26 Guang Lin , Chao Li , Jianhai Zhang , Toshihisa Tanaka , Qibin Zhao

Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for…

机器人学 · 计算机科学 2023-01-27 Mathias Lechner , Alexander Amini , Daniela Rus , Thomas A. Henzinger

Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this paper, we identify an overlooked problem of adversarial training…

机器学习 · 计算机科学 2020-09-24 Wonseok Lee , Hanbit Lee , Sang-goo Lee