English
Related papers

Related papers: RobustBench: a standardized adversarial robustness…

200 papers

Multimodal Large Language Models (MLLMs) increasingly support dynamic image resolutions. However, current evaluation paradigms primarily assess semantic performance, overlooking the critical question of resolution robustness - whether…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Chenxu Li , Zhicai Wang , Yuan Sheng , Xingyu Zhu , Yanbin Hao , Xiang Wang

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

This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning, presenting a well-structured review of up-to-date techniques to assess the vulnerability of various types of deep learning models to adversarial…

Machine Learning · Computer Science 2021-08-25 Wenjie Ruan , Xinping Yi , Xiaowei Huang

Most adversarial attacks and defenses focus on perturbations within small $\ell_p$-norm constraints. However, $\ell_p$ threat models cannot capture all relevant semantics-preserving perturbations, and hence, the scope of robustness…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Marcel Kollovieh , Lukas Gosch , Marten Lienen , Yan Scholten , Leo Schwinn , Stephan Günnemann

Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense's inner workings or approaches based on an ensemble of fixed attacks, none of which may…

Machine Learning · Computer Science 2021-10-28 Chengyuan Yao , Pavol Bielik , Petar Tsankov , Martin Vechev

Benefiting from large-scale pre-training, we have witnessed significant performance boost on the popular Visual Question Answering (VQA) task. Despite rapid progress, it remains unclear whether these state-of-the-art (SOTA) models are…

Computer Vision and Pattern Recognition · Computer Science 2021-08-16 Linjie Li , Jie Lei , Zhe Gan , Jingjing Liu

Dataset bias is a problem in adversarial machine learning, especially in the evaluation of defenses. An adversarial attack or defense algorithm may show better results on the reported dataset than can be replicated on other datasets. Even…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Camilo Pestana , Wei Liu , David Glance , Ajmal Mian

The transition from Cloud-Native to AI-Native architectures is fundamentally reshaping software engineering, replacing deterministic microservices with probabilistic agentic services. However, this shift renders traditional black-box…

Software Engineering · Computer Science 2026-01-15 Zirui Wang , Guangba Yu , Michael R. Lyu

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

Machine Learning · Computer Science 2023-09-06 Ruihan Zhang , Peixin Zhang , Jun Sun

Current research on defending against adversarial examples focuses primarily on achieving robustness against a single attack type such as $\ell_2$ or $\ell_{\infty}$-bounded attacks. However, the space of possible perturbations is much…

Machine Learning · Computer Science 2024-10-10 Sihui Dai , Chong Xiang , Tong Wu , Prateek Mittal

Robustness to adversarial attacks is typically evaluated with adversarial accuracy. While essential, this metric does not capture all aspects of robustness and in particular leaves out the question of how many perturbations can be found for…

Machine Learning · Computer Science 2023-08-14 Raphael Olivier , Bhiksha Raj

Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep neural networks. Since then, extensive efforts have been devoted to enhancing the robustness of deep networks via specialized learning algorithms and…

Machine Learning · Computer Science 2020-03-27 Minghao Guo , Yuzhe Yang , Rui Xu , Ziwei Liu , Dahua Lin

Adversarial patch attacks threaten the reliability of modern vision models. We present PatchMap, the first spatially exhaustive benchmark of patch placement, built by evaluating over 1.5e8 forward passes on ImageNet validation images.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Shai Kimhi , Avi Mendlson , Moshe Kimhi

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…

Computer Vision and Pattern Recognition · Computer Science 2021-09-08 Omid Poursaeed , Tianxing Jiang , Harry Yang , Serge Belongie , SerNam Lim

Robustness of neural networks has recently attracted a great amount of interest. The many investigations in this area lack a precise common foundation of robustness concepts. Therefore, in this paper, we propose a rigorous and flexible…

Machine Learning · Computer Science 2021-06-01 Alessandro Tibo , Manfred Jaeger , Kim G. Larsen

We introduce AutoAdvExBench, a benchmark to evaluate if large language models (LLMs) can autonomously exploit defenses to adversarial examples. Unlike existing security benchmarks that often serve as proxies for real-world tasks, bench…

Cryptography and Security · Computer Science 2025-03-04 Nicholas Carlini , Javier Rando , Edoardo Debenedetti , Milad Nasr , Florian Tramèr

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

Computation and Language · Computer Science 2025-09-22 Zhaofeng Wu , Michihiro Yasunaga , Andrew Cohen , Yoon Kim , Asli Celikyilmaz , Marjan Ghazvininejad

Optimizing prediction accuracy can come at the expense of fairness. Towards minimizing discrimination against a group, fair machine learning algorithms strive to equalize the behavior of a model across different groups, by imposing a…

Machine Learning · Statistics 2020-06-17 Hongyan Chang , Ta Duy Nguyen , Sasi Kumar Murakonda , Ehsan Kazemi , Reza Shokri

As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the behaviors of these black boxes. However, existing…

Machine Learning · Computer Science 2020-11-13 Himabindu Lakkaraju , Nino Arsov , Osbert Bastani

Adversarial robustness corresponds to the susceptibility of deep neural networks to imperceptible perturbations made at test time. In the context of image tasks, many algorithms have been proposed to make neural networks robust to…

Computer Vision and Pattern Recognition · Computer Science 2020-12-03 Pranjal Awasthi , George Yu , Chun-Sung Ferng , Andrew Tomkins , Da-Cheng Juan