English
Related papers

Related papers: A Closer Look at Adversarial Suffix Learning for J…

200 papers

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…

Cryptography and Security · Computer Science 2025-02-06 Xunguang Wang , Daoyuan Wu , Zhenlan Ji , Zongjie Li , Pingchuan Ma , Shuai Wang , Yingjiu Li , Yang Liu , Ning Liu , Juergen Rahmel

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…

Artificial Intelligence · Computer Science 2026-04-03 Hamin Koo , Minseon Kim , Jaehyung Kim

We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts or separate attacker models, self-jailbreaking requires no…

Computation and Language · Computer Science 2026-04-10 Devang Kulshreshtha , Hang Su , Haibo Jin , Chinmay Hegde , Haohan Wang

Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats,…

Cryptography and Security · Computer Science 2024-06-21 Jiongxiao Wang , Jiazhao Li , Yiquan Li , Xiangyu Qi , Junjie Hu , Yixuan Li , Patrick McDaniel , Muhao Chen , Bo Li , Chaowei Xiao

Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model…

Machine Learning · Computer Science 2025-05-20 Hana Satou , Alan Mitkiy

Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification…

Machine Learning · Computer Science 2018-01-15 Akram Erraqabi , Aristide Baratin , Yoshua Bengio , Simon Lacoste-Julien

Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques…

Machine Learning · Computer Science 2021-09-09 Dou Goodman , Xingjian Li , Ji Liu , Dejing Dou , Tao Wei

Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common application. These models excel at multi-step reasoning tasks, but their safety properties are not…

Computation and Language · Computer Science 2025-10-21 Yushi Yang , Shreyansh Padarha , Andrew Lee , Adam Mahdi

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Computation and Language · Computer Science 2023-05-30 Xuanjie Fang , Sijie Cheng , Yang Liu , Wei Wang

Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e.g., via byte…

Computation and Language · Computer Science 2024-07-29 Nilanjana Das , Edward Raff , Manas Gaur

Deep learning models can be fooled by small $l_p$-norm adversarial perturbations and natural perturbations in terms of attributes. Although the robustness against each perturbation has been explored, it remains a challenge to address the…

Machine Learning · Computer Science 2023-04-11 Dashan Gao , Yunce Zhao , Yinghua Yao , Zeqi Zhang , Bifei Mao , Xin Yao

As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreaking prompts that bypass moderation and alignment. Drawing from…

The rapid deployment of Large Language Models (LLMs) has created an urgent need for enhanced security and privacy measures in Machine Learning (ML). LLMs are increasingly being used to process untrusted text inputs and even generate…

Cryptography and Security · Computer Science 2025-12-15 Andrew Adiletta , Kathryn Adiletta , Kemal Derya , Berk Sunar

Beyond the success story of adversarial training (AT) in the recent text domain on top of pre-trained language models (PLMs), our empirical study showcases the inconsistent gains from AT on some tasks, e.g. commonsense reasoning, named…

Computation and Language · Computer Science 2023-05-09 Hongqiu Wu , Yongxiang Liu , Hanwen Shi , Hai Zhao , Min Zhang

Many-shot jailbreaking circumvents the safety alignment of LLMs by exploiting their ability to process long input sequences. To achieve this, the malicious target prompt is prefixed with hundreds of fabricated conversational exchanges…

Computation and Language · Computer Science 2025-06-16 Avery Ma , Yangchen Pan , Amir-massoud Farahmand

Transfer-based adversarial attacks raise a severe threat to real-world deep learning systems since they do not require access to target models. Adversarial training (AT), which is recognized as the strongest defense against white-box…

Cryptography and Security · Computer Science 2023-10-17 Yulong Yang , Chenhao Lin , Xiang Ji , Qiwei Tian , Qian Li , Hongshan Yang , Zhibo Wang , Chao Shen

Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Xiaojun Jia , Yong Zhang , Baoyuan Wu , Jue Wang , Xiaochun Cao

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more…

Cryptography and Security · Computer Science 2025-05-27 Haoyu Wang , Zeyu Qin , Yifei Zhao , Chao Du , Min Lin , Xueqian Wang , Tianyu Pang

Large Language Models (LLMs) exhibit substantial capabilities yet encounter challenges, including hallucination, outdated knowledge, and untraceable reasoning processes. Retrieval-augmented generation (RAG) has emerged as a promising…

Artificial Intelligence · Computer Science 2024-06-03 Feiteng Fang , Yuelin Bai , Shiwen Ni , Min Yang , Xiaojun Chen , Ruifeng Xu

The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated text detectors have been proposed to mitigate these risks,…

Computation and Language · Computer Science 2025-10-31 Yize Cheng , Vinu Sankar Sadasivan , Mehrdad Saberi , Shoumik Saha , Soheil Feizi
‹ Prev 1 8 9 10 Next ›