English
Related papers

Related papers: Getting a-Round Guarantees: Floating-Point Attacks…

200 papers

The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable robustness to problems with more general and structured…

Machine Learning · Computer Science 2022-01-13 Aounon Kumar , Tom Goldstein

Randomized smoothing, a method to certify a classifier's decision on an input is invariant under adversarial noise, offers attractive advantages over other certification methods. It operates in a black-box and so certification is not…

Machine Learning · Computer Science 2020-06-09 Jamie Hayes

Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small adversarial change of an originally with high confidence correctly classified input leads to a wrong classification again with high…

Machine Learning · Computer Science 2017-11-07 Matthias Hein , Maksym Andriushchenko

The current state-of-the-art defense methods against adversarial examples typically focus on improving either empirical or certified robustness. Among them, adversarially trained (AT) models produce empirical state-of-the-art defense…

Machine Learning · Computer Science 2022-08-02 Jay Nandy , Sudipan Saha , Wynne Hsu , Mong Li Lee , Xiao Xiang Zhu

Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences. Although certified…

Machine Learning · Computer Science 2023-06-13 Piersilvio De Bartolomeis , Jacob Clarysse , Amartya Sanyal , Fanny Yang

A range of defense methods have been proposed to improve the robustness of neural networks on adversarial examples, among which provable defense methods have been demonstrated to be effective to train neural networks that are certifiably…

Machine Learning · Computer Science 2021-01-21 Mengting Xu , Tao Zhang , Zhongnian Li , Daoqiang Zhang

We propose and investigate probabilistic guarantees for the adversarial robustness of classification algorithms. While traditional formal verification approaches for robustness are intractable and sampling-based approaches do not provide…

Machine Learning · Computer Science 2025-11-11 Peter Blohm , Patrick Indri , Thomas Gärtner , Sagar Malhotra

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed to defend against…

Cryptography and Security · Computer Science 2020-07-21 Binghui Wang , Xiaoyu Cao , Jinyuan jia , Neil Zhenqiang Gong

Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, networks trained only to optimize for training accuracy can often be fooled by adversarial examples - slightly perturbed inputs that…

Machine Learning · Computer Science 2019-02-19 Vincent Tjeng , Kai Xiao , Russ Tedrake

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

Machine Learning · Computer Science 2024-09-09 Hanbin Hong , Xinyu Zhang , Binghui Wang , Zhongjie Ba , Yuan Hong

Adversarial examples pose a security threat to many critical systems built on neural networks. While certified training improves robustness, it also decreases accuracy noticeably. Despite various proposals for addressing this issue, the…

Machine Learning · Statistics 2024-06-21 Ruihan Zhang , Jun Sun

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Robotics · Computer Science 2020-03-10 Björn Lütjens , Michael Everett , Jonathan P. How

Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering existing defenses…

Machine Learning · Computer Science 2024-10-25 Anupriya Kumari , Devansh Bhardwaj , Sukrit Jindal

Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they in general do not provide any guarantees, leaving them…

Machine Learning · Computer Science 2024-03-19 Shijie Liu , Andrew C. Cullen , Paul Montague , Sarah M. Erfani , Benjamin I. P. Rubinstein

Robustness is critical for machine learning (ML) classifiers to ensure consistent performance in real-world applications where models may encounter corrupted or adversarial inputs. In particular, assessing the robustness of classifiers to…

Machine Learning · Computer Science 2024-09-06 Georg Siedel , Ekagra Gupta , Andrey Morozov

While certified robustness is widely promoted as a solution to adversarial examples in Artificial Intelligence systems, significant challenges remain before these techniques can be meaningfully deployed in real-world applications. We…

Cryptography and Security · Computer Science 2025-08-12 Andrew C. Cullen , Paul Montague , Sarah M. Erfani , Benjamin I. P. Rubinstein

Randomized smoothing is a recent and celebrated solution to certify the robustness of any classifier. While it indeed provides a theoretical robustness against adversarial attacks, the dimensionality of current classifiers necessarily…

Cryptography and Security · Computer Science 2022-05-02 Thibault Maho , Teddy Furon , Erwan Le Merrer

Researchers have developed neural network verification algorithms motivated by the need to characterize the robustness of deep neural networks. The verifiers aspire to answer whether a neural network guarantees certain properties with…

Machine Learning · Computer Science 2021-10-04 Kai Jia , Martin Rinard

The possibility of errors in human-engineered formal verification software, such as model checkers, poses a serious threat to the purpose of these tools. An established approach to mitigate this problem are certificates -- lightweight,…

Logic in Computer Science · Computer Science 2025-01-22 Krishnendu Chatterjee , Tim Quatmann , Maximilian Schäffeler , Maximilian Weininger , Tobias Winkler , Daniel Zilken

In safety-critical machine learning applications, it is crucial to defend models against adversarial attacks -- small modifications of the input that change the predictions. Besides rigorously studied $\ell_p$-bounded additive…

Machine Learning · Computer Science 2022-08-16 Mikhail Pautov , Nurislam Tursynbek , Marina Munkhoeva , Nikita Muravev , Aleksandr Petiushko , Ivan Oseledets