English
Related papers

Related papers: Adversarial Robustness Limits via Scaling-Law and …

200 papers

Adversarial training is an effective methodology for training deep neural networks that are robust against adversarial, norm-bounded perturbations. However, the computational cost of adversarial training grows prohibitively as the size of…

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Machine Learning · Computer Science 2025-06-06 Nikolaus Howe , Ian McKenzie , Oskar Hollinsworth , Michał Zajac , Tom Tseng , Aaron Tucker , Pierre-Luc Bacon , Adam Gleave

Decision making and learning in the presence of uncertainty has attracted significant attention in view of the increasing need to achieve robust and reliable operations. In the case where uncertainty stems from the presence of adversarial…

Machine Learning · Computer Science 2024-03-25 André Bertolace , Konstatinos Gatsis , Kostas Margellos

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…

Robotics · Computer Science 2023-01-27 Mathias Lechner , Alexander Amini , Daniela Rus , Thomas A. Henzinger

In this work we introduce Salient Information Preserving Adversarial Training (SIP-AT), an intuitive method for relieving the robustness-accuracy trade-off incurred by traditional adversarial training. SIP-AT uses salient image regions to…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Timothy Redgrave , Adam Czajka

Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand these factors, we…

Machine Learning · Statistics 2022-07-05 Elvis Dohmatob , Alberto Bietti

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

Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the…

Machine Learning · Computer Science 2019-02-25 Gavin Weiguang Ding , Kry Yik Chau Lui , Xiaomeng Jin , Luyu Wang , Ruitong Huang

A small but growing body of work has shown that machine learning models which better align with human vision have also exhibited higher robustness to adversarial examples, raising the question: can human-like perception make models more…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Blaine Hoak , Kunyang Li , Patrick McDaniel

For sensitive problems, such as medical imaging or fraud detection, Neural Network (NN) adoption has been slow due to concerns about their reliability, leading to a number of algorithms for explaining their decisions. NNs have also been…

Machine Learning · Computer Science 2019-11-06 Walt Woods , Jack Chen , Christof Teuscher

Adversarial robustness is a research area that has recently received a lot of attention in the quest for trustworthy artificial intelligence. However, recent works on adversarial robustness have focused on supervised learning where it is…

Machine Learning · Computer Science 2023-08-09 Dongyoon Yang , Insung Kong , Yongdai Kim

Adversarial attacks are widely used to identify model vulnerabilities; however, their validity as proxies for robustness to random perturbations remains debated. We ask whether an adversarial example provides a representative estimate of…

Machine Learning · Computer Science 2026-01-27 Giulio Rossolini

Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logits from one clean model to guide learning of another one…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Jiequan Cui , Shu Liu , Liwei Wang , Jiaya Jia

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

Adversarial attacks can deceive neural networks by adding tiny perturbations to their input data. Ensemble defenses, which are trained to minimize attack transferability among sub-models, offer a promising research direction to improve…

Machine Learning · Computer Science 2022-11-16 Yunrui Yu , Xitong Gao , Cheng-Zhong Xu

Several recent works have developed methods for training classifiers that are certifiably robust against norm-bounded adversarial perturbations. These methods assume that all the adversarial transformations are equally important, which is…

Machine Learning · Computer Science 2019-03-06 Xiao Zhang , David Evans

We show that there may exist an inherent tension between the goal of adversarial robustness and that of standard generalization. Specifically, training robust models may not only be more resource-consuming, but also lead to a reduction of…

Machine Learning · Statistics 2019-09-10 Dimitris Tsipras , Shibani Santurkar , Logan Engstrom , Alexander Turner , Aleksander Madry

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…

Machine Learning · Computer Science 2019-08-28 Aditi Raghunathan , Sang Michael Xie , Fanny Yang , John C. Duchi , Percy Liang

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Levente Halmosi , Bálint Mohos , Márk Jelasity

Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Apostolos Modas