English
Related papers

Related papers: Semantics-Preserving Adversarial Training

200 papers

Adversarial training (AT) is a prominent technique employed by deep learning models to defend against adversarial attacks, and to some extent, enhance model robustness. However, there are three main drawbacks of the existing AT-based…

Image and Video Processing · Electrical Eng. & Systems 2026-03-31 X. Peng , D. Zhou , G. Sun , J. Shi , L. Wu

Deep neural networks (DNNs) are sensitive to adversarial examples, resulting in fragile and unreliable performance in the real world. Although adversarial training (AT) is currently one of the most effective methodologies to robustify DNNs,…

Machine Learning · Computer Science 2023-03-01 Yize Li , Pu Zhao , Xue Lin , Bhavya Kailkhura , Ryan Goldhahn

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples/attacks, raising concerns about their reliability in safety-critical applications. A number of defense methods have been proposed to train robust DNNs resistant…

Machine Learning · Computer Science 2021-04-23 Yujing Jiang , Xingjun Ma , Sarah Monazam Erfani , James Bailey

It is known that Deep Neural networks (DNNs) are vulnerable to adversarial attacks, and the adversarial robustness of DNNs could be improved by adding adversarial noises to training data (e.g., the standard adversarial training (SAT)).…

Image and Video Processing · Electrical Eng. & Systems 2022-06-23 Linhai Ma , Liang Liang

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

Adversarial Training (AT) is one of the most effective methods to enhance the robustness of Deep Neural Networks (DNNs). However, existing AT methods suffer from an inherent accuracy-robustness trade-off. Previous works have studied this…

Machine Learning · Computer Science 2025-05-28 Yanyun Wang , Li Liu , Zi Liang , Yi R. , Fung , Qingqing Ye , Haibo Hu

Adversarial training is a promising strategy for enhancing model robustness against adversarial attacks. However, its impact on generalization under substantial data distribution shifts in audio classification remains largely unexplored. To…

Machine Learning · Computer Science 2025-07-21 René Heinrich , Lukas Rauch , Bernhard Sick , Christoph Scholz

Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the…

Computation and Language · Computer Science 2022-11-23 Shunsuke Kitada , Hitoshi Iyatomi

Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most…

Machine Learning · Computer Science 2023-07-17 Olukorede Fakorede , Ashutosh Kumar Nirala , Modeste Atsague , Jin Tian

Deep Neural Networks (DNNs) are expected to provide explanation for users to understand their black-box predictions. Saliency map is a common form of explanation illustrating the heatmap of feature attributions, but it suffers from noise in…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Rui Xu , Wenkang Qin , Peixiang Huang , Hao Wang , Lin Luo

We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning. RAT is designed to enhance robustness of the output distribution of class prediction for a given data against input perturbation.…

Computer Vision and Pattern Recognition · Computer Science 2019-11-19 Teppei Suzuki , Ikuro Sato

Adversarial training and its variants have become de facto standards for learning robust deep neural networks. In this paper, we explore the landscape around adversarial training in a bid to uncover its limits. We systematically study the…

Machine Learning · Statistics 2021-03-31 Sven Gowal , Chongli Qin , Jonathan Uesato , Timothy Mann , Pushmeet Kohli

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data,…

Image and Video Processing · Electrical Eng. & Systems 2024-03-12 Shuai Li , Xiaoguang Ma , Shancheng Jiang , Lu Meng

In response to the threat of adversarial examples, adversarial training provides an attractive option for enhancing the model robustness by training models on online-augmented adversarial examples. However, most of the existing adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-12-02 Jia-Li Yin , Lehui Xie , Wanqing Zhu , Ximeng Liu , Bo-Hao Chen

Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can drastically impair the network's performance. Many defense methods have been proposed for improving…

Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks. In contrast to the individually…

Machine Learning · Computer Science 2017-09-19 Sungrae Park , Jun-Keon Park , Su-Jin Shin , Il-Chul Moon

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

Computation and Language · Computer Science 2023-02-09 Hongqiu Wu , Ruixue Ding , Hai Zhao , Pengjun Xie , Fei Huang , Min Zhang

The existence of real-world adversarial examples (commonly in the form of patches) poses a serious threat for the use of deep learning models in safety-critical computer vision tasks such as visual perception in autonomous driving. This…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Giulio Rossolini , Federico Nesti , Gianluca D'Amico , Saasha Nair , Alessandro Biondi , Giorgio Buttazzo

Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted…

Machine Learning · Statistics 2020-04-28 Florian Tramèr , Alexey Kurakin , Nicolas Papernot , Ian Goodfellow , Dan Boneh , Patrick McDaniel

Performance-critical machine learning models should be robust to input perturbations not seen during training. Adversarial training is a method for improving a model's robustness to some perturbations by including them in the training…

Machine Learning · Computer Science 2018-07-24 Angus Galloway , Thomas Tanay , Graham W. Taylor