English
Related papers

Related papers: Advancing Adversarial Suffix Transfer Learning on …

200 papers

Adversarial prompt attacks can significantly alter the reliability of Retrieval-Augmented Generation (RAG) systems by re-ranking them to produce incorrect outputs. In this paper, we present a novel method that applies Differential Evolution…

Artificial Intelligence · Computer Science 2025-07-22 Jerry Wang , Fang Yu

Language models (LMs) are often used as zero-shot or few-shot classifiers by scoring label words, but they remain fragile to adversarial prompts. Prior work typically optimizes task- or model-specific triggers, making results difficult to…

Computation and Language · Computer Science 2025-12-10 Sampriti Soor , Suklav Ghosh , Arijit Sur

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

Machine Learning · Computer Science 2024-10-28 Samuel Jacob Chacko , Sajib Biswas , Chashi Mahiul Islam , Fatema Tabassum Liza , Xiuwen Liu

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended…

Computation and Language · Computer Science 2025-11-10 Chung-En Sun , Xiaodong Liu , Weiwei Yang , Tsui-Wei Weng , Hao Cheng , Aidan San , Michel Galley , Jianfeng Gao

Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate…

Machine Learning · Computer Science 2024-06-06 Xiaojun Jia , Tianyu Pang , Chao Du , Yihao Huang , Jindong Gu , Yang Liu , Xiaochun Cao , Min Lin

Adversarial attacks present a critical challenge to deep neural networks' robustness, particularly in transfer scenarios across different model architectures. However, the transferability of adversarial attacks faces a fundamental dilemma…

Machine Learning · Computer Science 2025-11-04 Zenghao Niu , Weicheng Xie , Siyang Song , Zitong Yu , Feng Liu , Linlin Shen

With the great advancements in large language models (LLMs), adversarial attacks against LLMs have recently attracted increasing attention. We found that pre-existing adversarial attack methodologies exhibit limited transferability and are…

Computation and Language · Computer Science 2024-09-10 Zelin Li , Kehai Chen , Lemao Liu , Xuefeng Bai , Mingming Yang , Yang Xiang , Min Zhang

Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the black-box adversarial setting, where the adversary needs to…

Machine Learning · Computer Science 2022-03-15 Yinpeng Dong , Shuyu Cheng , Tianyu Pang , Hang Su , Jun Zhu

Large Language Models (LLMs) have achieved remarkable success across diverse tasks, yet they remain vulnerable to adversarial attacks, notably the well-known jailbreak attack. In particular, the Greedy Coordinate Gradient (GCG) attack has…

Machine Learning · Computer Science 2025-03-04 Yihao Zhang , Zeming Wei

Language models are vulnerable to short adversarial suffixes that can reliably alter predictions. Previous works usually find such suffixes with gradient search or rule-based methods, but these are brittle and often tied to a single task or…

Computation and Language · Computer Science 2025-12-10 Sampriti Soor , Suklav Ghosh , Arijit Sur

The advancement of Pre-Trained Language Models (PTLMs) and Large Language Models (LLMs) has led to their widespread adoption across diverse applications. Despite their success, these models remain vulnerable to attacks that exploit their…

Computation and Language · Computer Science 2025-06-30 Mohamed Ahmed , Mohamed Abdelmouty , Mingyu Kim , Gunvanth Kandula , Alex Park , James C. Davis

The rapid advancement of large language models (LLMs) has led to significant improvements in their capabilities, but also to increased concerns about their alignment with human values and intentions. Current alignment strategies, including…

Computation and Language · Computer Science 2025-01-10 Hantao Lou , Jiaming Ji , Kaile Wang , Yaodong Yang

Despite recent success on various tasks, deep learning techniques still perform poorly on adversarial examples with small perturbations. While optimization-based methods for adversarial attacks are well-explored in the field of computer…

Computation and Language · Computer Science 2023-06-09 Lifan Yuan , Yichi Zhang , Yangyi Chen , Wei Wei

Adversarial attacks on Graph Neural Networks aim to perturb the performance of the learner by carefully modifying the graph topology and node attributes. Existing methods achieve attack stealthiness by constraining the modification budget…

Machine Learning · Computer Science 2025-06-10 Kai Yuan , Jiahao Zhang , Yidi Wang , Xiaobing Pei

Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly…

Computation and Language · Computer Science 2024-04-19 Pengfei Wu , Jiahao Liu , Zhuocheng Gong , Qifan Wang , Jinpeng Li , Jingang Wang , Xunliang Cai , Dongyan Zhao

The safety defense methods of Large language models(LLMs) stays limited because the dangerous prompts are manually curated to just few known attack types, which fails to keep pace with emerging varieties. Recent studies found that attaching…

Computation and Language · Computer Science 2024-06-05 Hao Wang , Hao Li , Minlie Huang , Lei Sha

Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some…

Computation and Language · Computer Science 2023-12-22 Andy Zou , Zifan Wang , Nicholas Carlini , Milad Nasr , J. Zico Kolter , Matt Fredrikson

Deep neural networks are known to be vulnerable to adversarial examples crafted by adding human-imperceptible perturbations to the benign input. After achieving nearly 100% attack success rates in white-box setting, more focus is shifted to…

Computer Vision and Pattern Recognition · Computer Science 2023-07-07 Xu Han , Anmin Liu , Chenxuan Yao , Yanbo Fan , Kun He

Multi-label audio tagging consists of assigning sets of tags to audio recordings. At inference time, thresholds are applied on the confidence scores outputted by a probabilistic classifier, in order to decide which classes are detected…

Artificial Intelligence · Computer Science 2021-03-02 Thomas Pellegrini , Timothée Masquelier

Adversarial attacks, particularly \textbf{targeted} transfer-based attacks, can be used to assess the adversarial robustness of large visual-language models (VLMs), allowing for a more thorough examination of potential security flaws before…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Qi Guo , Shanmin Pang , Xiaojun Jia , Yang Liu , Qing Guo