English
Related papers

Related papers: Alignment-Enhanced Decoding:Defending via Token-Le…

200 papers

In this study, we introduce RePD, an innovative attack Retrieval-based Prompt Decomposition framework designed to mitigate the risk of jailbreak attacks on large language models (LLMs). Despite rigorous pretraining and finetuning focused on…

Cryptography and Security · Computer Science 2024-12-02 Peiran Wang , Xiaogeng Liu , Chaowei Xiao

Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing approaches often rely on static heuristics or stochastic search, rendering them brittle…

Machine Learning · Computer Science 2026-05-22 Huilin Zhou , Jian Zhao , Yilu Zhong , Zhen Liang , Xiuyuan Chen , Yuchen Yuan , Tianle Zhang , Chi Zhang , Lan Zhang , Xuelong Li

Diffusion language models (DLMs) generate tokens in parallel through iterative denoising, which can reduce latency and enable bidirectional conditioning. However, the safety risks posed by jailbreak attacks that exploit this inference…

Artificial Intelligence · Computer Science 2026-02-18 Shojiro Yamabe , Jun Sakuma

An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users. This is usually achieved by tuning the model in a way that enhances desired behaviors…

Computation and Language · Computer Science 2024-06-04 Yotam Wolf , Noam Wies , Oshri Avnery , Yoav Levine , Amnon Shashua

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,…

We present Entropy Adaptive Decoding (EAD), a novel approach for efficient language model inference that dynamically switches between different-sized models based on prediction uncertainty. By monitoring rolling entropy in model logit…

Machine Learning · Computer Science 2025-02-12 Toby Simonds

Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…

Computation and Language · Computer Science 2024-10-08 Sarah Ball , Frauke Kreuter , Nina Panickssery

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…

Cryptography and Security · Computer Science 2025-08-07 Xiaohu Li , Yunfeng Ning , Zepeng Bao , Mayi Xu , Jianhao Chen , Tieyun Qian

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

Computation and Language · Computer Science 2025-05-13 Brian R. Y. Huang , Maximilian Li , Leonard Tang

Large Language Models (LLMs) have achieved remarkable success but remain highly susceptible to jailbreak attacks, in which adversarial prompts coerce models into generating harmful, unethical, or policy-violating outputs. Such attacks pose…

Cryptography and Security · Computer Science 2026-05-07 Feiyue Xu , Hongsheng Hu , Chaoxiang He , Sheng Hang , Hanqing Hu , Xiuming Liu , Yubo Zhao , Zhengyan Zhou , Bin Benjamin Zhu , Shi-Feng Sun , Dawu Gu , Shuo Wang

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

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Cryptography and Security · Computer Science 2024-12-03 Erick Galinkin , Martin Sablotny

Large language models have drawn significant attention to the challenge of safe alignment, especially regarding jailbreak attacks that circumvent security measures to produce harmful content. To address the limitations of existing methods…

Artificial Intelligence · Computer Science 2024-11-05 Hanqing Liu , Lifeng Zhou , Huanqian Yan

Machine learning classification systems are susceptible to poor performance when trained with incorrect ground truth labels, even when data is well-curated by expert annotators. As machine learning becomes more widespread, it is…

Machine Learning · Computer Science 2026-01-16 Zan Chaudhry , Noam H. Rotenberg , Brian Caffo , Craig K. Jones , Haris I. Sair

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Computation and Language · Computer Science 2024-12-18 Weixiong Zheng , Peijian Zeng , Yiwei Li , Hongyan Wu , Nankai Lin , Junhao Chen , Aimin Yang , Yongmei Zhou

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law…

Machine Learning · Computer Science 2026-03-20 Xiangwen Wang , Ananth Balashankar , Varun Chandrasekaran

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, but their vulnerability to jailbreak attacks poses significant security risks. This survey paper presents a comprehensive analysis…

Computation and Language · Computer Science 2024-12-18 Tarun Raheja , Nilay Pochhi , F. D. C. M. Curie

Vision-language models (VLMs) have become central to tasks such as visual question answering, image captioning, and text-to-image generation. However, their outputs are highly sensitive to prompt variations, which can reveal vulnerabilities…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Aarush Noheria , Yuguang Yao

We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. First, we demonstrate how to successfully leverage access to logprobs for jailbreaking: we initially design an adversarial prompt…

Cryptography and Security · Computer Science 2025-04-21 Maksym Andriushchenko , Francesco Croce , Nicolas Flammarion

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulnerable to jailbreak attacks that bypass safety guardrails.…

Cryptography and Security · Computer Science 2025-04-29 Julien Piet , Xiao Huang , Dennis Jacob , Annabella Chow , Maha Alrashed , Geng Zhao , Zhanhao Hu , Chawin Sitawarin , Basel Alomair , David Wagner
‹ Prev 1 4 5 6 7 8 10 Next ›