English
Related papers

Related papers: Confidence-Calibrated Adversarial Training: Genera…

200 papers

We integrate contrastive learning (CL) with adversarial learning to co-optimize the robustness and accuracy of code models. Different from existing works, we show that code obfuscation, a standard code transformation operation, provides…

Machine Learning · Computer Science 2023-03-07 Jinghan Jia , Shashank Srikant , Tamara Mitrovska , Chuang Gan , Shiyu Chang , Sijia Liu , Una-May O'Reilly

Adversarial training is often formulated as a min-max problem, however, concentrating only on the worst adversarial examples causes alternating repetitive confusion of the model, i.e., previously defended or correctly classified samples are…

Machine Learning · Computer Science 2023-12-13 Qian Li , Yuxiao Hu , Yinpeng Dong , Dongxiao Zhang , Yuntian Chen

A major drawback of adversarially robust models, in particular for large scale datasets like ImageNet, is the extremely long training time compared to standard ones. Moreover, models should be robust not only to one $l_p$-threat model but…

Machine Learning · Computer Science 2022-08-09 Francesco Croce , Matthias Hein

Despite remarkable success in practice, modern machine learning models have been found to be susceptible to adversarial attacks that make human-imperceptible perturbations to the data, but result in serious and potentially dangerous…

Machine Learning · Computer Science 2020-08-18 Lin Chen , Yifei Min , Mingrui Zhang , Amin Karbasi

Large language models remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Defending against novel jailbreaks represents a critical challenge in AI safety. Adversarial training -- designed to make…

Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. However, most existing AT methods adopt a specific attack to craft adversarial examples,…

Machine Learning · Computer Science 2020-11-20 Yinpeng Dong , Zhijie Deng , Tianyu Pang , Hang Su , Jun Zhu

Supervised learning models are challenged by the intrinsic complexities of training data such as outliers and minority subpopulations and intentional attacks at inference time with adversarial samples. While traditional robust learning…

Machine Learning · Computer Science 2023-09-12 Shu Hu , Zhenhuan Yang , Xin Wang , Yiming Ying , Siwei Lyu

Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this paper, we identify an overlooked problem of adversarial training…

Machine Learning · Computer Science 2020-09-24 Wonseok Lee , Hanbit Lee , Sang-goo Lee

Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization…

Machine Learning · Computer Science 2022-12-21 Zhiyuan Zhang , Wei Li , Ruihan Bao , Keiko Harimoto , Yunfang Wu , Xu Sun

The neural network (NN) becomes one of the most heated type of models in various signal processing applications. However, NNs are extremely vulnerable to adversarial examples (AEs). To defend AEs, adversarial training (AT) is believed to be…

Machine Learning · Computer Science 2023-08-31 Mingyuan Fan , Yang Liu , Cen Chen

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…

Deep convolutional neural networks are susceptible to adversarial attacks. They can be easily deceived to give an incorrect output by adding a tiny perturbation to the input. This presents a great challenge in making CNNs robust against…

Machine Learning · Computer Science 2021-04-21 Yunrui Yu , Xitong Gao , Cheng-Zhong Xu

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have…

Cryptography and Security · Computer Science 2021-03-16 Zhe Zhao , Guangke Chen , Jingyi Wang , Yiwei Yang , Fu Song , Jun Sun

Deep Neural Networks (DNNs) are known to be vulnerable to various adversarial perturbations. To address the safety concerns arising from these vulnerabilities, adversarial training (AT) has emerged as one of the most effective paradigms for…

Machine Learning · Computer Science 2025-11-18 Rui Wang , Zeming Wei , Xiyue Zhang , Meng Sun

Deep learning-based discriminative classifiers, despite their remarkable success, remain vulnerable to adversarial examples that can mislead model predictions. While adversarial training can enhance robustness, it fails to address the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Chunheng Zhao , Pierluigi Pisu , Gurcan Comert , Negash Begashaw , Varghese Vaidyan , Nina Christine Hubig

Adversarial training is the most effective method to obtain adversarial robustness for deep neural networks by directly involving adversarial samples in the training procedure. To obtain an accurate and robust model, the weighted-average…

Machine Learning · Computer Science 2024-10-23 Zhiyu Xue , Haohan Wang , Yao Qin , Ramtin Pedarsani

Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Emanuele Ledda , Daniele Angioni , Giorgio Piras , Giorgio Fumera , Battista Biggio , Fabio Roli

Modern machine learning and deep learning models are shown to be vulnerable when testing data are slightly perturbed. Existing theoretical studies of adversarial training algorithms mostly focus on either adversarial training losses or…

Machine Learning · Statistics 2021-04-07 Yue Xing , Qifan Song , Guang Cheng

Recent work has shown that language models' refusal behavior is primarily encoded in a single direction in their latent space, making it vulnerable to targeted attacks. Although Latent Adversarial Training (LAT) attempts to improve…

Computation and Language · Computer Science 2025-04-29 Alexandra Abbas , Nora Petrova , Helios Ael Lyons , Natalia Perez-Campanero

A Very recent trend has emerged to couple the notion of interpretability and adversarial robustness, unlike earlier efforts which solely focused on good interpretations or robustness against adversaries. Works have shown that adversarially…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Puneet Mangla , Vedant Singh , Vineeth N Balasubramanian