English
Related papers

Related papers: Causal Front-Door Adjustment for Robust Jailbreak …

200 papers

Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…

Machine Learning · Computer Science 2024-02-28 Heegyu Kim , Sehyun Yuk , Hyunsouk Cho

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However, exposing a model's internal reasoning process introduces additional…

Artificial Intelligence · Computer Science 2026-05-20 Zheng Lin , Zhenxing Niu , Haoxuan Ji , Yuzhe Huang , Haichang Gao

In this paper, we investigate the safety mechanisms of instruction fine-tuned large language models (LLMs). We discover that re-weighting MLP neurons can significantly compromise a model's safety, especially for MLPs in end-of-sentence…

Computation and Language · Computer Science 2024-10-15 Yifan Luo , Zhennan Zhou , Meitan Wang , Bin Dong

Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation space. Recent works show that initializing attacks via self-transfer from other prompts…

Cryptography and Security · Computer Science 2025-10-09 Amit Levi , Rom Himelstein , Yaniv Nemcovsky , Avi Mendelson , Chaim Baskin

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…

Cryptography and Security · Computer Science 2025-06-02 Xin Yi , Yue Li , Dongsheng Shi , Linlin Wang , Xiaoling Wang , Liang He

Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we…

Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query…

Cryptography and Security · Computer Science 2026-05-19 Ziwei Wang , Jing Chen , Ruichao Liang , Zhi Wang , Yebo Feng , Ju Jia , Ruiying Du , Cong Wu , Yang Liu

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

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

Cryptography and Security · Computer Science 2024-06-14 Xuan Chen , Yuzhou Nie , Lu Yan , Yunshu Mao , Wenbo Guo , Xiangyu Zhang

Large language models (LLMs) have revolutionized artificial intelligence, but their increasing deployment across critical domains has raised concerns about their abnormal behaviors when faced with malicious attacks. Such vulnerability…

Software Engineering · Computer Science 2025-04-02 Shide Zhou , Tianlin Li , Kailong Wang , Yihao Huang , Ling Shi , Yang Liu , Haoyu Wang

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

Cryptography and Security · Computer Science 2024-04-15 Tianyu Zhang , Zixuan Zhao , Jiaqi Huang , Jingyu Hua , Sheng Zhong

Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art models. Existing alignment-based and guardrail methods…

Cryptography and Security · Computer Science 2026-04-21 Bo Yan , Weikai Lin , Yada Zhu , Song Wang

The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak…

Computation and Language · Computer Science 2024-03-25 Zezhong Wang , Fangkai Yang , Lu Wang , Pu Zhao , Hongru Wang , Liang Chen , Qingwei Lin , Kam-Fai Wong

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…

Cryptography and Security · Computer Science 2025-09-05 Chuhan Zhang , Ye Zhang , Bowen Shi , Yuyou Gan , Tianyu Du , Shouling Ji , Dazhan Deng , Yingcai Wu

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to…

Computation and Language · Computer Science 2024-06-07 Javier Rando , Francesco Croce , Kryštof Mitka , Stepan Shabalin , Maksym Andriushchenko , Nicolas Flammarion , Florian Tramèr

Despite the widespread application of large language models (LLMs) across various tasks, recent studies indicate that they are susceptible to jailbreak attacks, which can render their defense mechanisms ineffective. However, previous…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Jiawei Chen , Xiao Yang , Zhengwei Fang , Yu Tian , Yinpeng Dong , Zhaoxia Yin , Hang Su

The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensity to trust information from authoritative sources, such as…

Computation and Language · Computer Science 2025-07-21 Liang Lin , Zhihao Xu , Xuehai Tang , Shi Liu , Biyu Zhou , Fuqing Zhu , Jizhong Han , Songlin Hu

Defense in large language models (LLMs) is crucial to counter the numerous attackers exploiting these systems to generate harmful content through manipulated prompts, known as jailbreak attacks. Although many defense strategies have been…

Cryptography and Security · Computer Science 2024-12-11 Bocheng Chen , Hanqing Guo , Qiben Yan

Jailbreak attacks represent one of the most sophisticated threats to the security of large language models (LLMs). To deal with such risks, we introduce an innovative framework that can help evaluate the effectiveness of jailbreak attacks…

Computation and Language · Computer Science 2025-03-19 Dong Shu , Chong Zhang , Mingyu Jin , Zihao Zhou , Lingyao Li , Yongfeng Zhang

Large Language Models (LLMs) have shown impressive capabilities across various tasks but remain vulnerable to meticulously crafted jailbreak attacks. In this paper, we identify a critical safety gap: while LLMs are adept at detecting…

Computation and Language · Computer Science 2025-05-20 Peng Ding , Jun Kuang , Zongyu Wang , Xuezhi Cao , Xunliang Cai , Jiajun Chen , Shujian Huang
‹ Prev 1 8 9 10 Next ›