English
Related papers

Related papers: Refusal-Trained LLMs Are Easily Jailbroken As Brow…

200 papers

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

Artificial Intelligence · Computer Science 2025-08-20 Yuzhi Tang , Tianxiao Li , Elizabeth Li , Chris J. Maddison , Honghua Dong , Yangjun Ruan

Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass…

Computation and Language · Computer Science 2026-02-26 Xinpeng Wang , Mingyang Wang , Yihong Liu , Hinrich Schütze , Barbara Plank

Large language models (LLMs) have fueled many intelligent web agents, but most existing ones perform far from satisfying in real-world web navigation tasks due to three factors: (1) the complexity of HTML text data (2) versatility of…

Computation and Language · Computer Science 2024-10-15 Hanyu Lai , Xiao Liu , Iat Long Iong , Shuntian Yao , Yuxuan Chen , Pengbo Shen , Hao Yu , Hanchen Zhang , Xiaohan Zhang , Yuxiao Dong , Jie Tang

It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely…

Machine Learning · Computer Science 2024-02-22 Jonas Geiping , Alex Stein , Manli Shu , Khalid Saifullah , Yuxin Wen , Tom Goldstein

Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) services due to their exceptional proficiency in understanding and generating human-like text. LLM chatbots, in particular, have seen widespread adoption,…

Cryptography and Security · Computer Science 2024-02-14 Gelei Deng , Yi Liu , Yuekang Li , Kailong Wang , Ying Zhang , Zefeng Li , Haoyu Wang , Tianwei Zhang , Yang Liu

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…

Artificial Intelligence · Computer Science 2026-04-21 Hailin Liu , Eugene Ilyushin , Jie Ni , Min Zhu

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

Multiagent Systems · Computer Science 2026-05-12 Xiaolin Sun , Zixuan Liu , Yibin Hu , Zizhan Zheng

Large language models (LLMs) are increasingly deployed as tool-using agents, shifting safety concerns from harmful text generation to harmful task completion. Deployed systems often condition on user profiles or persistent memory, yet agent…

Artificial Intelligence · Computer Science 2026-03-18 Caglar Yildirim

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Cryptography and Security · Computer Science 2026-05-12 Matteo Lupinacci , Francesco Aurelio Pironti , Francesco Blefari , Francesco Romeo , Luigi Arena , Angelo Furfaro

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

Cryptography and Security · Computer Science 2024-10-23 Xiaohan Fu , Shuheng Li , Zihan Wang , Yihao Liu , Rajesh K. Gupta , Taylor Berg-Kirkpatrick , Earlence Fernandes

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…

Artificial Intelligence · Computer Science 2026-02-18 Sanidhya Vijayvargiya , Aditya Bharat Soni , Xuhui Zhou , Zora Zhiruo Wang , Nouha Dziri , Graham Neubig , Maarten Sap

Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common application. These models excel at multi-step reasoning tasks, but their safety properties are not…

Computation and Language · Computer Science 2025-10-21 Yushi Yang , Shreyansh Padarha , Andrew Lee , Adam Mahdi

Large language models (LLMs) have exhibited great potential in autonomously completing tasks across real-world applications. Despite this, these LLM agents introduce unexpected safety risks when operating in interactive environments.…

Computation and Language · Computer Science 2024-10-08 Tongxin Yuan , Zhiwei He , Lingzhong Dong , Yiming Wang , Ruijie Zhao , Tian Xia , Lizhen Xu , Binglin Zhou , Fangqi Li , Zhuosheng Zhang , Rui Wang , Gongshen Liu

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Computation and Language · Computer Science 2025-10-01 Yuyou Zhang , Miao Li , William Han , Yihang Yao , Zhepeng Cen , Ding Zhao

Large Language Models (LLMs) are set to reshape cybersecurity by augmenting red and blue team operations. Red teams can exploit LLMs to plan attacks, craft phishing content, simulate adversaries, and generate exploit code. Conversely, blue…

Cryptography and Security · Computer Science 2025-06-17 Alsharif Abuadbba , Chris Hicks , Kristen Moore , Vasilios Mavroudis , Burak Hasircioglu , Diksha Goel , Piers Jennings

Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that…

Machine Learning · Computer Science 2024-11-15 Yifan Zeng , Yiran Wu , Xiao Zhang , Huazheng Wang , Qingyun Wu

AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content. Our work exposes the inherent cross-lingual vulnerability of these safety mechanisms, resulting from the…

Computation and Language · Computer Science 2024-01-30 Zheng-Xin Yong , Cristina Menghini , Stephen H. Bach

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its…

Machine Learning · Computer Science 2024-11-01 Andy Arditi , Oscar Obeso , Aaquib Syed , Daniel Paleka , Nina Panickssery , Wes Gurnee , Neel Nanda

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Computation and Language · Computer Science 2025-10-08 Harethah Abu Shairah , Hasan Abed Al Kader Hammoud , Bernard Ghanem , George Turkiyyah

Refusals - instances where large language models (LLMs) decline or fail to fully execute user instructions - are crucial for both AI safety and AI capabilities and the reduction of hallucinations in particular. These behaviors are learned…

Artificial Intelligence · Computer Science 2024-12-24 Alexander von Recum , Christoph Schnabl , Gabor Hollbeck , Silas Alberti , Philip Blinde , Marvin von Hagen