English
Related papers

Related papers: Reasoning as an Attack Surface: Adaptive Evolution…

200 papers

Large Reasoning Models (LRMs) leverage Chain-of-Thought (CoT) reasoning to solve complex tasks, but this explicit reasoning process introduces a critical vulnerability: adversarial manipulation of the thought chain itself, known as…

Machine Learning · Computer Science 2026-02-13 Zihao Xue , Zhen Bi , Long Ma , Zhenlin Hu , Yan Wang , Xueshu Chen , Zhenfang Liu , Kang Zhao , Jie Xiao , Jungang Lou

Jailbreaking large language models (LLMs) has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts to elicit…

Cryptography and Security · Computer Science 2026-02-23 Sri Durga Sai Sowmya Kadali , Evangelos E. Papalexakis

Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack strategies, there is no unified understanding on why some…

Computation and Language · Computer Science 2024-12-04 Yuping Lin , Pengfei He , Han Xu , Yue Xing , Makoto Yamada , Hui Liu , Jiliang Tang

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

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

Cryptography and Security · Computer Science 2025-11-11 Haonan Shi , Guoli Wang , Tu Ouyang , An Wang

Defending large language models (LLMs) against jailbreak attacks is essential for their safe and reliable deployment. Existing defenses often rely on shallow pattern matching, which struggles to generalize to novel and unseen attack…

Artificial Intelligence · Computer Science 2025-08-06 Rui Pu , Chaozhuo Li , Rui Ha , Litian Zhang , Lirong Qiu , Xi Zhang

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…

Cryptography and Security · Computer Science 2025-08-14 Boyuan Chen , Minghao Shao , Abdul Basit , Siddharth Garg , Muhammad Shafique

Large language models (LLMs) demonstrate significant reasoning capabilities, particularly through long chain-of-thought (CoT) processes, which can be elicited by reinforcement learning (RL). However, prolonged CoT reasoning presents…

Computation and Language · Computer Science 2025-12-29 Haoyuan Wu , Xueyi Chen , Rui Ming , Jilong Gao , Shoubo Hu , Zhuolun He , Bei Yu

Large Language Models (LLMs) have demonstrated strong reasoning capabilities through \emph{Chain-of-Thought} (CoT) prompting, which enables step-by-step intermediate reasoning. However, explicit CoT methods rely on discrete token-level…

Computation and Language · Computer Science 2025-11-11 Zhikang Chen , Sen Cui , Deheng Ye , Yu Zhang , Yatao Bian , Tingting Zhu

LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks that elicit harmful behaviors without explicit policy violations. While a growing body of…

Cryptography and Security · Computer Science 2026-05-05 Jindong Li , Ying Liu , Yali Fu , Jinjing Zhu , Leyao Wang , Menglin Yang , Rex Ying

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to…

Cryptography and Security · Computer Science 2026-01-29 Harsh Chaudhari , Ethan Rathbun , Hanna Foerster , Jamie Hayes , Matthew Jagielski , Milad Nasr , Ilia Shumailov , Alina Oprea

Despite their superior performance on a wide range of domains, large language models (LLMs) remain vulnerable to misuse for generating harmful content, a risk that has been further amplified by various jailbreak attacks. Existing jailbreak…

Cryptography and Security · Computer Science 2025-10-27 Yukun Jiang , Mingjie Li , Michael Backes , Yang Zhang

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

Computation and Language · Computer Science 2025-04-18 Charlotte Siska , Anush Sankaran

Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning…

Artificial Intelligence · Computer Science 2025-04-02 Yu Cui , Bryan Hooi , Yujun Cai , Yiwei Wang

Chain-of-thought (CoT) prompting is a de-facto standard technique to elicit reasoning-like responses from large language models (LLMs), allowing them to spell out individual steps before giving a final answer. While the resemblance to…

Artificial Intelligence · Computer Science 2026-02-26 Gregor Bachmann , Yichen Jiang , Seyed Mohsen Moosavi Dezfooli , Moin Nabi

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

Artificial Intelligence · Computer Science 2026-05-12 Dongcheng Zhang , Yi Zhang , Yuxin Chen , An Zhang , Xiang Wang , Chaochao Lu

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…

Computation and Language · Computer Science 2026-05-05 Jialin Song , Xiaodong Liu , Weiwei Yang , Wuyang Chen , Mingqian Feng , Xuekai Zhu , Jianfeng Gao

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

Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable…

Machine Learning · Computer Science 2024-06-17 Alexander Robey , Eric Wong , Hamed Hassani , George J. Pappas

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…

Computation and Language · Computer Science 2023-09-06 Peiyi Wang , Lei Li , Liang Chen , Feifan Song , Binghuai Lin , Yunbo Cao , Tianyu Liu , Zhifang Sui