English
Related papers

Related papers: Understanding Robust Overfitting of Adversarial Tr…

200 papers

Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…

Machine Learning · Computer Science 2024-11-06 Junhao Dong , Xinghua Qu , Z. Jane Wang , Yew-Soon Ong

Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of…

Machine Learning · Computer Science 2025-03-21 Lei Yu , Virginie Do , Karen Hambardzumyan , Nicola Cancedda

Adversarial training is a widely used method to improve the robustness of deep neural networks (DNNs) over adversarial perturbations. However, it is empirically observed that adversarial training on over-parameterized networks often suffers…

Machine Learning · Statistics 2024-01-25 Zhongjie Shi , Fanghui Liu , Yuan Cao , Johan A. K. Suykens

Adversarial training is often formulated as a min-max problem, however, concentrating only on the worst adversarial examples causes alternating repetitive confusion of the model, i.e., previously defended or correctly classified samples are…

Machine Learning · Computer Science 2023-12-13 Qian Li , Yuxiao Hu , Yinpeng Dong , Dongxiao Zhang , Yuntian Chen

Adversarial training, as one of the most effective defense methods against adversarial attacks, tends to learn an inclusive decision boundary to increase the robustness of deep learning models. However, due to the large and unnecessary…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Xiaoyu Liang , Yaguan Qian , Jianchang Huang , Xiang Ling , Bin Wang , Chunming Wu , Wassim Swaileh

Deep neural networks are vulnerable to adversarial attacks. Recent studies about adversarial robustness focus on the loss landscape in the parameter space since it is related to optimization and generalization performance. These studies…

Machine Learning · Computer Science 2023-03-07 Sekitoshi Kanai , Masanori Yamada , Hiroshi Takahashi , Yuki Yamanaka , Yasutoshi Ida

Recent years have witnessed significant progresses in deep Reinforcement Learning (RL). Empowered with large scale neural networks, carefully designed architectures, novel training algorithms and massively parallel computing devices,…

Machine Learning · Computer Science 2018-04-23 Chiyuan Zhang , Oriol Vinyals , Remi Munos , Samy Bengio

Adversarial training (AT) is one of the most effective strategies for promoting model robustness. However, recent benchmarks show that most of the proposed improvements on AT are less effective than simply early stopping the training…

Machine Learning · Computer Science 2021-04-01 Tianyu Pang , Xiao Yang , Yinpeng Dong , Hang Su , Jun Zhu

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Cryptography and Security · Computer Science 2020-09-30 Philip Sperl , Konstantin Böttinger

Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propose a new algorithm,…

Machine Learning · Computer Science 2020-02-19 Minhao Cheng , Qi Lei , Pin-Yu Chen , Inderjit Dhillon , Cho-Jui Hsieh

Adversarial training (AT) has become the de-facto standard to obtain models robust against adversarial examples. However, AT exhibits severe robust overfitting: cross-entropy loss on adversarial examples, so-called robust loss, decreases…

Machine Learning · Computer Science 2021-10-07 David Stutz , Matthias Hein , Bernt Schiele

It has been consistently reported that many machine learning models are susceptible to adversarial attacks i.e., small additive adversarial perturbations applied to data points can cause misclassification. Adversarial training using…

Machine Learning · Statistics 2021-07-15 Hossein Taheri , Ramtin Pedarsani , Christos Thrampoulidis

Adversarial training yields robust models against a specific threat model, e.g., $L_\infty$ adversarial examples. Typically robustness does not generalize to previously unseen threat models, e.g., other $L_p$ norms, or larger perturbations.…

Machine Learning · Computer Science 2020-07-01 David Stutz , Matthias Hein , Bernt Schiele

Adversarial training based on the minimax formulation is necessary for obtaining adversarial robustness of trained models. However, it is conservative or even pessimistic so that it sometimes hurts the natural generalization. In this paper,…

Machine Learning · Computer Science 2020-09-08 Jingfeng Zhang , Xilie Xu , Bo Han , Gang Niu , Lizhen Cui , Masashi Sugiyama , Mohan Kankanhalli

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Machine Learning · Computer Science 2024-03-15 Daiwei Yu , Zhuorong Li , Lina Wei , Canghong Jin , Yun Zhang , Sixian Chan

Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed…

Machine Learning · Statistics 2015-03-24 Ian J. Goodfellow , Jonathon Shlens , Christian Szegedy

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…

Machine Learning · Computer Science 2022-05-25 Shudong Zhang , Haichang Gao , Tianwei Zhang , Yunyi Zhou , Zihui Wu

While existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real-world settings. In many such cases although test data might not be…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Tejas Gokhale , Rushil Anirudh , Bhavya Kailkhura , Jayaraman J. Thiagarajan , Chitta Baral , Yezhou Yang

Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs). Most existing AT approaches can be grouped into restricted and unrestricted approaches. Restricted AT…

Machine Learning · Computer Science 2020-04-14 Haidong Xie , Xueshuang Xiang , Naijin Liu , Bin Dong

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to confuse the model into making a mistake. Such examples pose a serious threat to the applicability of machine-learning-based systems,…

Machine Learning · Computer Science 2023-10-18 Peiyu Xiong , Michael Tegegn , Jaskeerat Singh Sarin , Shubhraneel Pal , Julia Rubin