English
Related papers

Related papers: Localization then Neutralization: Gradient-guided …

200 papers

We propose the first general-purpose gradient-based attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix,…

Computation and Language · Computer Science 2021-04-29 Chuan Guo , Alexandre Sablayrolles , Hervé Jégou , Douwe Kiela

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

Cryptography and Security · Computer Science 2026-05-25 Xueyi Li , Zhuoneng Zhou , Zitao Liu , Yongdong Wu

Adversarial attacks make their success in DNNs, and among them, gradient-based algorithms become one of the mainstreams. Based on the linearity hypothesis, under $\ell_\infty$ constraint, $sign$ operation applied to the gradients is a good…

Computer Vision and Pattern Recognition · Computer Science 2022-02-07 Yaya Cheng , Jingkuan Song , Xiaosu Zhu , Qilong Zhang , Lianli Gao , Heng Tao Shen

Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens…

Computation and Language · Computer Science 2026-05-07 Jiawei Wu , Doudou Zhou

Fast gradient sign attack series are popular methods that are used to generate adversarial examples. However, most of the approaches based on fast gradient sign attack series cannot balance the indistinguishability and transferability due…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Junhua Zou , Yexin Duan , Boyu Li , Wu Zhang , Yu Pan , Zhisong Pan

Deep neural networks have demonstrated remarkable effectiveness across a wide range of tasks such as semantic segmentation. Nevertheless, these networks are vulnerable to adversarial attacks that add imperceptible perturbations to the input…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Kira Maag , Roman Resner , Asja Fischer

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

Cryptography and Security · Computer Science 2023-12-15 Sicheng Zhu , Ruiyi Zhang , Bang An , Gang Wu , Joe Barrow , Zichao Wang , Furong Huang , Ani Nenkova , Tong Sun

Recent studies have shown that graph convolution networks (GCNs) are vulnerable to carefully designed attacks, which aim to cause misclassification of a specific node on the graph with unnoticeable perturbations. However, a vast majority of…

Cryptography and Security · Computer Science 2020-04-30 Jihong Wang , Minnan Luo , Fnu Suya , Jundong Li , Zijiang Yang , Qinghua Zheng

Automatic modulation classification (AMC) using the Deep Neural Network (DNN) approach outperforms the traditional classification techniques, even in the presence of challenging wireless channel environments. However, the adversarial…

Machine Learning · Computer Science 2022-06-01 Eyad Shtaiwi , Ahmed El Ouadrhiri , Majid Moradikia , Salma Sultana , Ahmed Abdelhadi , Zhu Han

Adversarial attacks have been fairly explored for computer vision and vision-language models. However, the avenue of adversarial attack for the vision language segmentation models (VLSMs) is still under-explored, especially for medical…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Anjila Budathoki , Manish Dhakal

Generative Adversarial Networks (GANs) have been widely used in various application scenarios. Since the production of a commercial GAN requires substantial computational and human resources, the copyright protection of GANs is urgently…

Cryptography and Security · Computer Science 2024-08-08 Guanlin Li , Guowen Xu , Han Qiu , Shangwei Guo , Run Wang , Jiwei Li , Tianwei Zhang , Rongxing Lu

With the flourishing prosperity of generative models, manipulated facial images have become increasingly accessible, raising concerns regarding privacy infringement and societal trust. In response, proactive defense strategies embed…

Cryptography and Security · Computer Science 2025-10-03 Yue Li , Linying Xue , Dongdong Lin , Qiushi Li , Hui Tian , Hongxia Wang

Deep neural networks (DNNs) have been applied in a wide range of applications,e.g.,face recognition and image classification; however,they are vulnerable to adversarial examples. By adding a small amount of imperceptible perturbations,an…

Computer Vision and Pattern Recognition · Computer Science 2021-02-16 Fengting Li , Xuankai Liu , Xiaoli Zhang , Qi Li , Kun Sun , Kang Li

The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common…

Computation and Language · Computer Science 2026-01-23 Rishit Chugh

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Jindong Gu , Hengshuang Zhao , Volker Tresp , Philip Torr

Input transformation based defense strategies fall short in defending against strong adversarial attacks. Some successful defenses adopt approaches that either increase the randomness within the applied transformations, or make the defense…

Computer Vision and Pattern Recognition · Computer Science 2020-05-08 Ankita Shukla , Pavan Turaga , Saket Anand

Numerous studies have demonstrated the susceptibility of deep neural networks (DNNs) to subtle adversarial perturbations, prompting the development of many advanced adversarial defense methods aimed at mitigating adversarial attacks.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Linyu Tang , Lei Zhang

The state-of-the-art approaches in Generative Adversarial Networks (GANs) are able to learn a mapping function from one image domain to another with unpaired image data. However, these methods often produce artifacts and can only be able to…

Computer Vision and Pattern Recognition · Computer Science 2019-08-29 Hao Tang , Dan Xu , Nicu Sebe , Yan Yan

Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use the gradient or by…

Machine Learning · Computer Science 2022-01-14 Mitra Alirezaei , Tolga Tasdizen

Software developers frequently hard-code credentials such as passwords, generic secrets, private keys, and generic tokens in software repositories, even though it is strictly advised against due to the severe threat to the security of the…

Cryptography and Security · Computer Science 2025-06-17 Chidera Biringa , Gokhan Kul