English
Related papers

Related papers: Reasoning Hijacking: The Fragility of Reasoning Al…

200 papers

Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understand context and recognize user intent. This creates exploitable vulnerabilities…

Artificial Intelligence · Computer Science 2026-04-28 Ahmed M. Hussain , Salahuddin Salahuddin

Despite the recent advancement in large language models (LLMs) and their high performances across numerous benchmarks, recent research has unveiled that LLMs suffer from hallucinations and unfaithful reasoning. This work studies a specific…

Computation and Language · Computer Science 2024-04-09 Bangzheng Li , Ben Zhou , Fei Wang , Xingyu Fu , Dan Roth , Muhao Chen

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation…

Artificial Intelligence · Computer Science 2025-10-27 Jingnan Zheng , Xiangtian Ji , Yijun Lu , Chenhang Cui , Weixiang Zhao , Gelei Deng , Zhenkai Liang , An Zhang , Tat-Seng Chua

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter method called \textit{Prompt Learning}. However, during the…

Computation and Language · Computer Science 2022-09-07 Yundi Shi , Piji Li , Changchun Yin , Zhaoyang Han , Lu Zhou , Zhe Liu

Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing…

Cryptography and Security · Computer Science 2026-02-12 Yu Yan , Sheng Sun , Shengjia Cheng , Teli Liu , Mingfeng Li , Min Liu

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise decision-making demands more than raw language proficiency--LLMs…

Computation and Language · Computer Science 2025-02-24 Ang Li , Yichuan Mo , Mingjie Li , Yifei Wang , Yisen Wang

Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibility of hijacking…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Changyue Li , Jiaying Li , Youliang Yuan , Jiaming He , Zhicong Huang , Pinjia He

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

Large Reasoning Models (LRMs) have significantly advanced beyond traditional Large Language Models (LLMs) with their exceptional logical reasoning capabilities, yet these improvements introduce heightened safety risks. When subjected to…

Cryptography and Security · Computer Science 2025-06-04 Yang Yao , Xuan Tong , Ruofan Wang , Yixu Wang , Lujundong Li , Liang Liu , Yan Teng , Yingchun Wang

Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety…

Cryptography and Security · Computer Science 2025-05-27 Qingsong Zou , Jingyu Xiao , Qing Li , Zhi Yan , Yuhang Wang , Li Xu , Wenxuan Wang , Kuofeng Gao , Ruoyu Li , Yong Jiang

Despite substantial advancements in aligning large language models (LLMs) with human values, current safety mechanisms remain susceptible to jailbreak attacks. We hypothesize that this vulnerability stems from distributional discrepancies…

Computation and Language · Computer Science 2026-04-27 Jingyu Peng , Maolin Wang , Nan Wang , Jiatong Li , Yuchen Li , Yuyang Ye , Wanyu Wang , Pengyue Jia , Kai Zhang , Xiangyu Zhao

The proliferation of powerful large language models (LLMs) has necessitated robust safety alignment, yet these models remain vulnerable to evolving adversarial attacks, including multi-turn jailbreaks that iteratively search for successful…

Cryptography and Security · Computer Science 2026-02-04 Weiliang Zhao , Jinjun Peng , Daniel Ben-Levi , Zhou Yu , Junfeng Yang

Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…

Cryptography and Security · Computer Science 2024-10-31 David Glukhov , Ziwen Han , Ilia Shumailov , Vardan Papyan , Nicolas Papernot

Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…

Cryptography and Security · Computer Science 2026-05-20 Hongyu Cai , Arjun Arunasalam , Yiming Liang , Antonio Bianchi , Z. Berkay Celik

Recently, Large Language Models (LLMs) have garnered significant attention for their exceptional natural language processing capabilities. However, concerns about their trustworthiness remain unresolved, particularly in addressing…

Computation and Language · Computer Science 2025-01-29 Yue Huang , Jingyu Tang , Dongping Chen , Bingda Tang , Yao Wan , Lichao Sun , Philip S. Yu , Xiangliang Zhang

Critiques are important for enhancing the performance of Large Language Models (LLMs), enabling both self-improvement and constructive feedback for others by identifying flaws and suggesting improvements. However, evaluating the critique…

Computation and Language · Computer Science 2025-01-27 Zhengyang Tang , Ziniu Li , Zhenyang Xiao , Tian Ding , Ruoyu Sun , Benyou Wang , Dayiheng Liu , Fei Huang , Tianyu Liu , Bowen Yu , Junyang Lin

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

Cryptography and Security · Computer Science 2025-08-15 Jinhwa Kim , Ian G. Harris

We investigate the robustness of reasoning models trained for step-by-step problem solving by introducing query-agnostic adversarial triggers - short, irrelevant text that, when appended to math problems, systematically mislead models to…

In this paper, we observe that current models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability. This is evidenced by a high incidence of false positives-solutions that reach the…

Computation and Language · Computer Science 2026-04-20 Youliang Yuan , Qiuyang Mang , Jingbang Chen , Hong Wan , Xiaoyuan Liu , Junjielong Xu , Jen-tse Huang , Wenxuan Wang , Wenxiang Jiao , Pinjia He