English
Related papers

Related papers: Criticality Leveraged Adversarial Training (CLAT) …

200 papers

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Yinghe Zhang , Chi Liu , Shuai Zhou , Sheng Shen , Peng Gui

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that…

Machine Learning · Computer Science 2026-04-15 Shaopeng Fu , Di Wang

Adversarial Training (AT), which is commonly accepted as one of the most effective approaches defending against adversarial examples, can largely harm the standard performance, thus has limited usefulness on industrial-scale production and…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Xiaofeng Mao , Yuefeng Chen , Ranjie Duan , Yao Zhu , Gege Qi , Shaokai Ye , Xiaodan Li , Rong Zhang , Hui Xue

In the field of adversarial robustness, there is a common practice that adopts the single-step adversarial training for quickly developing adversarially robust models. However, the single-step adversarial training is most likely to cause…

Machine Learning · Computer Science 2021-06-30 Xiaosen Wang , Chuanbiao Song , Liwei Wang , Kun He

Deep learning models continue to advance in accuracy, yet they remain vulnerable to adversarial attacks, which often lead to the misclassification of adversarial examples. Adversarial training is used to mitigate this problem by increasing…

Computer Vision and Pattern Recognition · Computer Science 2024-02-20 Leo Hyun Park , Jaeuk Kim , Myung Gyo Oh , Jaewoo Park , Taekyoung Kwon

Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Futa Waseda , Saku Sugawara , Isao Echizen

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

Machine Learning · Computer Science 2025-10-29 Csaba Dékány , Stefan Balauca , Robin Staab , Dimitar I. Dimitrov , Martin Vechev

Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for…

Robotics · Computer Science 2023-01-27 Mathias Lechner , Alexander Amini , Daniela Rus , Thomas A. Henzinger

Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logits from one clean model to guide learning of another one…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Jiequan Cui , Shu Liu , Liwei Wang , Jiaya Jia

Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by adversarial attacks. These attacks add a small perturbation to the…

Machine Learning · Computer Science 2018-03-26 Rajeev Ranjan , Swami Sankaranarayanan , Carlos D. Castillo , Rama Chellappa

Self-supervised learning approach like contrastive learning is attached great attention in natural language processing. It uses pairs of training data augmentations to build a classification task for an encoder with well representation…

Computation and Language · Computer Science 2021-12-03 Deshui Miao , Jiaqi Zhang , Wenbo Xie , Jian Song , Xin Li , Lijuan Jia , Ning Guo

Existing adversarial training (AT) methods often suffer from incomplete perturbation, meaning that not all non-robust features are perturbed when generating adversarial examples (AEs). This results in residual correlations between…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Lilin Zhang , Chengpei Wu , Ning Yang

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

Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification. However, unlike humans, CNNs leverage spurious features, such as background information to make decisions.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Ke Wang , Harshitha Machiraju , Oh-Hyeon Choung , Michael Herzog , Pascal Frossard

With the tremendous advances in the architecture and scale of convolutional neural networks (CNNs) over the past few decades, they can easily reach or even exceed the performance of humans in certain tasks. However, a recently discovered…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Yanxi Li , Zhaohui Yang , Yunhe Wang , Chang Xu

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Machine Learning · Computer Science 2024-03-15 Daiwei Yu , Zhuorong Li , Lina Wei , Canghong Jin , Yun Zhang , Sixian Chan

Adversarial training often suffers from a robustness-accuracy trade-off, where achieving high robustness comes at the cost of accuracy. One approach to mitigate this trade-off is leveraging invariance regularization, which encourages model…

Machine Learning · Computer Science 2025-08-29 Futa Waseda , Ching-Chun Chang , Isao Echizen

Recommender systems play a pivotal role in mitigating information overload in various fields. Nonetheless, the inherent openness of these systems introduces vulnerabilities, allowing attackers to insert fake users into the system's training…

Information Retrieval · Computer Science 2024-09-27 Kaike Zhang , Qi Cao , Yunfan Wu , Fei Sun , Huawei Shen , Xueqi Cheng

For years, adversarial training has been extensively studied in natural language processing (NLP) settings. The main goal is to make models robust so that similar inputs derive in semantically similar outcomes, which is not a trivial…

Computation and Language · Computer Science 2021-09-21 Daniela N. Rim , DongNyeong Heo , Heeyoul Choi

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be…

Hardware Architecture · Computer Science 2023-12-22 Qing Zhang , Cheng Liu , Bo Liu , Haitong Huang , Ying Wang , Huawei Li , Xiaowei Li