English
Related papers

Related papers: TRYLOCK: Defense-in-Depth Against LLM Jailbreaks v…

200 papers

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

Variational quantum circuits face a critical trade-off between privacy and trainability. High expressivity required for robust privacy induces exponentially large dynamical Lie algebras. This structure inevitably leads to barren plateaus.…

Quantum Physics · Physics 2025-12-02 Chenyi Zhang , Tao Shang , Chao Guo , Ruohan He

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

Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assistance of LLMs has raised the challenge of "jailbreaking",…

Cryptography and Security · Computer Science 2024-09-02 Sibo Yi , Yule Liu , Zhen Sun , Tianshuo Cong , Xinlei He , Jiaxing Song , Ke Xu , Qi Li

A new generation of language models reasons entirely in continuous hidden states, producing no tokens and leaving no audit trail. We show that this silence creates a fundamentally new attack surface. ThoughtSteer perturbs a single embedding…

Machine Learning · Computer Science 2026-04-02 Swapnil Parekh

Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for defending against jailbreak attacks are primarily based on auxiliary models. These strategies, however, often require extensive data collection or…

Cryptography and Security · Computer Science 2025-11-21 Zhuoran Yang , Yanyong Zhang

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…

Cryptography and Security · Computer Science 2026-01-28 Shuang Liang , Zhihao Xu , Jiaqi Weng , Jialing Tao , Hui Xue , Xiting Wang

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…

Cryptography and Security · Computer Science 2024-10-08 Yiting Dong , Guobin Shen , Dongcheng Zhao , Xiang He , Yi Zeng

Large language models (LLMs) can still be jailbroken into producing harmful outputs despite safety alignment. Existing attacks show this vulnerability, but not the internal mechanisms that cause it. This study asks whether jailbreak success…

Computation and Language · Computer Science 2026-04-28 Nilanjana Das , Manas Gaur

Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concerns about the safety…

Cryptography and Security · Computer Science 2025-05-22 Taiye Chen , Zeming Wei , Ang Li , Yisen Wang

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

Cryptography and Security · Computer Science 2026-01-01 Yuan Xin , Dingfan Chen , Linyi Yang , Michael Backes , Xiao Zhang

Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the magnitude of answer vectors, but this creates a fundamental…

Machine Learning · Computer Science 2026-05-05 Haonan Zhang , Dongxia Wang , Yi Liu , Kexin Chen , Wenhai Wang

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

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…

Cryptography and Security · Computer Science 2026-05-29 Zikai Zhang , Rui Hu , Olivera Kotevska , Jiahao Xu

How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions,…

As large language models (LLMs) grow more powerful, ensuring their safety against misuse becomes crucial. While researchers have focused on developing robust defenses, no method has yet achieved complete invulnerability to attacks. We…

Computation and Language · Computer Science 2024-11-13 Alwin Peng , Julian Michael , Henry Sleight , Ethan Perez , Mrinank Sharma

Large Language Models (LLMs) are increasingly popular, powering a wide range of applications. Their widespread use has sparked concerns, especially through jailbreak attacks that bypass safety measures to produce harmful content. In this…

Cryptography and Security · Computer Science 2025-12-25 Zhengchun Shang , Wenlan Wei , Weiheng Bai

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

As multimodal reasoning improves the overall capabilities of Large Vision Language Models (LVLMs), recent studies have begun to explore safety-oriented reasoning, aiming to enhance safety awareness by analyzing potential safety risks during…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Fenghua Weng , Chaochao Lu , Xia Hu , Wenqi Shao , Wenjie Wang

Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional components. However, existing safety attribution methods…

Machine Learning · Computer Science 2026-03-25 Miao Yu , Siyuan Fu , Moayad Aloqaily , Zhenhong Zhou , Safa Otoum , Xing fan , Kun Wang , Yufei Guo , Qingsong Wen