English
Related papers

Related papers: Certified Robustness to Text Adversarial Attacks b…

200 papers

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Dong Lao , Yuxiang Zhang , Haniyeh Ehsani Oskouie , Yangchao Wu , Alex Wong , Stefano Soatto

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and…

Machine Learning · Computer Science 2020-11-03 Aditi Raghunathan , Jacob Steinhardt , Percy Liang

Strong theoretical guarantees of robustness can be given for ensembles of classifiers generated by input randomization. Specifically, an $\ell_2$ bounded adversary cannot alter the ensemble prediction generated by an additive isotropic…

Machine Learning · Computer Science 2020-02-28 Guang-He Lee , Yang Yuan , Shiyu Chang , Tommi S. Jaakkola

Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful content generation, LLMs are often still vulnerable to…

Machine Learning · Computer Science 2025-01-29 Ryo Hase , Md Rafi Ur Rashid , Ashley Lewis , Jing Liu , Toshiaki Koike-Akino , Kieran Parsons , Ye Wang

Adversarial attacks hamper the functionality and accuracy of Deep Neural Networks (DNNs) by meddling with subtle perturbations to their inputs.In this work, we propose a new Mask-based Adversarial Defense scheme (MAD) for DNNs to mitigate…

Machine Learning · Computer Science 2022-04-27 Weizhen Xu , Chenyi Zhang , Fangzhen Zhao , Liangda Fang

The study of provable adversarial robustness for deep neural networks (DNNs) has mainly focused on static supervised learning tasks such as image classification. However, DNNs have been used extensively in real-world adaptive tasks such as…

Machine Learning · Computer Science 2022-05-31 Aounon Kumar , Alexander Levine , Soheil Feizi

Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when…

Machine Learning · Computer Science 2023-04-13 Linyi Li , Tao Xie , Bo Li

Currently the most popular method of providing robustness certificates is randomized smoothing where an input is smoothed via some probability distribution. We propose a novel approach to randomized smoothing over multiplicative parameters.…

Machine Learning · Computer Science 2022-08-17 Nikita Muravev , Aleksandr Petiushko

This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel…

Cryptography and Security · Computer Science 2026-05-12 Zheng Lin , Zhenxing Niu , Haoxuan Ji , Haichang Gao

Explanation methods have emerged as an important tool to highlight the features responsible for the predictions of neural networks. There is mounting evidence that many explanation methods are rather unreliable and susceptible to malicious…

Computation and Language · Computer Science 2022-06-27 Shriya Atmakuri , Tejas Chheda , Dinesh Kandula , Nishant Yadav , Taesung Lee , Hessel Tuinhof

Machine learning models are vulnerable to adversarial attacks. One approach to addressing this vulnerability is certification, which focuses on models that are guaranteed to be robust for a given perturbation size. A drawback of recent…

Machine Learning · Computer Science 2020-10-07 Ryan Campbell , Chris Finlay , Adam M Oberman

Deep Neural Networks, despite their great success in diverse domains, are provably sensitive to small perturbations on correctly classified examples and lead to erroneous predictions. Recently, it was proposed that this behavior can be…

Machine Learning · Computer Science 2020-09-29 Nan Xu , Oluwaseyi Feyisetan , Abhinav Aggarwal , Zekun Xu , Nathanael Teissier

Modern machine learning models with very high accuracy have been shown to be vulnerable to small, adversarially chosen perturbations of the input. Given black-box access to a high-accuracy classifier $f$, we show how to construct a new…

Machine Learning · Computer Science 2019-12-17 Grzegorz Głuch , Rüdiger Urbanke

Randomized smoothing is a general technique for computing sample-dependent robustness guarantees against adversarial attacks for deep classifiers. Prior works on randomized smoothing against L_1 adversarial attacks use additive smoothing…

Machine Learning · Computer Science 2021-06-14 Alexander Levine , Soheil Feizi

We study certified robustness of machine learning classifiers against adversarial perturbations. In particular, we propose the first universally approximated certified robustness (UniCR) framework, which can approximate the robustness…

Machine Learning · Computer Science 2022-07-12 Hanbin Hong , Binghui Wang , Yuan Hong

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

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

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Computation and Language · Computer Science 2021-10-18 Wenkai Yang , Yankai Lin , Peng Li , Jie Zhou , Xu Sun

Adversarial attack serves as a major challenge for neural network models in NLP, which precludes the model's deployment in safety-critical applications. A recent line of work, detection-based defense, aims to distinguish adversarial…

Computation and Language · Computer Science 2023-02-07 Lingfeng Shen , Ze Zhang , Haiyun Jiang , Ying Chen

While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversarial attacks. Recently, there have emerged numerous efforts in adversarial defense. Among…

Machine Learning · Computer Science 2026-05-29 Yiran Qiao , Yu Yin , Chen Chen , Jing Ma