English
Related papers

Related papers: Understanding Adversarial Robustness: The Trade-of…

200 papers

Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence…

Machine Learning · Computer Science 2020-11-04 Tao Bai , Jinqi Luo , Jun Zhao

Adversarial training has been proven to be an effective technique for improving the adversarial robustness of models. However, there seems to be an inherent trade-off between optimizing the model for accuracy and robustness. To this end, we…

Computer Vision and Pattern Recognition · Computer Science 2020-08-20 Elahe Arani , Fahad Sarfraz , Bahram Zonooz

In adversarial machine learning, there was a common belief that robustness and accuracy hurt each other. The belief was challenged by recent studies where we can maintain the robustness and improve the accuracy. However, the other…

Machine Learning · Computer Science 2021-06-01 Jingfeng Zhang , Jianing Zhu , Gang Niu , Bo Han , Masashi Sugiyama , Mohan Kankanhalli

Adversarial training has proven to be effective in hardening networks against adversarial examples. However, the gained robustness is limited by network capacity and number of training samples. Consequently, to build more robust models, it…

Machine Learning · Computer Science 2020-06-02 Zheng Xu , Ali Shafahi , Tom Goldstein

There has been great interest in enhancing the robustness of neural network classifiers to defend against adversarial perturbations through adversarial training, while balancing the trade-off between robust accuracy and standard accuracy.…

Machine Learning · Computer Science 2022-10-24 Chester Holtz , Tsui-Wei Weng , Gal Mishne

The robustness of modern machine learning (ML) models has become an increasing concern within the community. The ability to subvert a model into making errant predictions using seemingly inconsequential changes to input is startling, as is…

Machine Learning · Computer Science 2023-06-19 Edward Raff , Michel Benaroch , Andrew L. Farris

Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Paul Gavrikov , Janis Keuper

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

Machine Learning · Computer Science 2020-07-13 Anh Bui , Trung Le , He Zhao , Paul Montague , Olivier deVel , Tamas Abraham , Dinh Phung

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings…

Machine Learning · Statistics 2019-09-06 Aleksander Madry , Aleksandar Makelov , Ludwig Schmidt , Dimitris Tsipras , Adrian Vladu

Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations…

Machine Learning · Statistics 2019-03-26 Arun Sai Suggala , Adarsh Prasad , Vaishnavh Nagarajan , Pradeep Ravikumar

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Machine Learning · Computer Science 2019-11-12 Bai Li , Changyou Chen , Wenlin Wang , Lawrence Carin

Deep neural networks are incredibly vulnerable to crafted, human-imperceptible adversarial perturbations. Although adversarial training (AT) has proven to be an effective defense approach, we find that the AT-trained models heavily rely on…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Binxiao Huang , Chaofan Tao , Rui Lin , Ngai Wong

Despite strong performance in numerous applications, the fragility of deep learning to input perturbations has raised serious questions about its use in safety-critical domains. While adversarial training can mitigate this issue in…

Machine Learning · Statistics 2021-11-01 Alexander Robey , Luiz F. O. Chamon , George J. Pappas , Hamed Hassani , Alejandro Ribeiro

Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small $\ell_\infty$-noise). For other perturbations, these defenses offer no guarantees and, at times, even…

Machine Learning · Computer Science 2019-10-21 Florian Tramèr , Dan Boneh

The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be {\it $\epsilon$-adversarially…

Machine Learning · Computer Science 2020-11-17 Yuxin Wen , Shuai Li , Kui Jia

Adversarial training shows promise as an approach for training models that are robust towards adversarial perturbation. In this paper, we explore some of the practical challenges of adversarial training. We present a sensitivity analysis…

Machine Learning · Computer Science 2019-05-13 Evelyn Duesterwald , Anupama Murthi , Ganesh Venkataraman , Mathieu Sinn , Deepak Vijaykeerthy

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…

Computation and Language · Computer Science 2023-12-12 Enes Altinisik , Hassan Sajjad , Husrev Taha Sencar , Safa Messaoud , Sanjay Chawla

Robustness of machine learning models to various adversarial and non-adversarial corruptions continues to be of interest. In this paper, we introduce the notion of the boundary thickness of a classifier, and we describe its connection with…

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions…

Machine Learning · Computer Science 2017-11-28 Andrew Slavin Ross , Finale Doshi-Velez

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…

Machine Learning · Computer Science 2025-10-16 Yisen Wang , Yichuan Mo , Hongjun Wang , Junyi Li , Zhouchen Lin