English
Related papers

Related papers: CoP: Agentic Red-teaming for Large Language Models…

200 papers

While Large Language Models (LLMs) are widely used, they remain susceptible to jailbreak prompts that can elicit harmful or inappropriate responses. This paper introduces STAR-Teaming, a novel black-box framework for automated red teaming…

Computation and Language · Computer Science 2026-04-22 MinJae Jung , YongTaek Lim , Chaeyun Kim , Junghwan Kim , Kihyun Kim , Minwoo Kim

Ramp merging is one of the bottlenecks in traffic systems, which commonly cause traffic congestion, accidents, and severe carbon emissions. In order to address this essential issue and enhance the safety and efficiency of connected and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-25 Senkang Hu , Zhengru Fang , Zihan Fang , Yiqin Deng , Xianhao Chen , Yuguang Fang , Sam Kwong

Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules. The challenge lies in ensuring that the agent consistently adheres to these rules and policies,…

Multiagent Systems · Computer Science 2025-08-26 Itay Nakash , George Kour , Koren Lazar , Matan Vetzler , Guy Uziel , Ateret Anaby-Tavor

Eliciting harmful behavior from large language models (LLMs) is an important task to ensure the proper alignment and safety of the models. Often when training LLMs, ethical guidelines are followed yet alignment failures may still be…

Cryptography and Security · Computer Science 2024-08-20 Robert J. Moss

Recent studies have discovered that large language models (LLM) may be ``fooled'' to output private information, including training data, system prompts, and personally identifiable information, under carefully crafted adversarial prompts.…

Cryptography and Security · Computer Science 2025-08-11 Yuzhou Nie , Zhun Wang , Ye Yu , Xian Wu , Xuandong Zhao , Wenbo Guo , Dawn Song

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

Computation and Language · Computer Science 2024-06-25 Simone Tedeschi , Felix Friedrich , Patrick Schramowski , Kristian Kersting , Roberto Navigli , Huu Nguyen , Bo Li

Autonomous agents powered by large language models (LLMs) perform complex tasks through long-horizon reasoning and tool interaction, where a fundamental trade-off arises between execution efficiency and reasoning robustness. Models at…

Computation and Language · Computer Science 2026-03-30 Wenbo Gao , Renxi Liu , Xian Wang , Fang Guo , Shuai Yang , Xi Chen , Hui-Ling Zhen , Hanting Chen , Weizhe Lin , Xiaosong Li , Yaoyuan Wang

Large Vision Language Models (VLMs) extend and enhance the perceptual abilities of Large Language Models (LLMs). Despite offering new possibilities for LLM applications, these advancements raise significant security and ethical concerns,…

Machine Learning · Computer Science 2024-07-23 Yi Liu , Chengjun Cai , Xiaoli Zhang , Xingliang Yuan , Cong Wang

Large Language Models (LLMs) have shown great ability in solving traditional natural language tasks and elementary reasoning tasks with appropriate prompting techniques. However, their ability is still limited in solving complicated science…

Computation and Language · Computer Science 2024-04-30 Pei Chen , Boran Han , Shuai Zhang

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

Cryptography and Security · Computer Science 2025-07-22 Pengfei Du

Many approaches to LLM red-teaming leverage an attacker LLM to discover jailbreaks against a target. Several of them task the attacker with identifying effective strategies through trial and error, resulting in a semantically limited range…

Cryptography and Security · Computer Science 2026-04-24 Jesse Zymet , Andy Luo , Swapnil Shinde , Sahil Wadhwa , Emily Chen

Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teaming methods for proactively assessing such vulnerabilities…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Yufan Liu , Wanqian Zhang , Huashan Chen , Lin Wang , Xiaojun Jia , Zheng Lin , Weiping Wang

Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of knowledge and understanding capabilities, but they have also been shown to be prone to illegal or unethical reactions when subjected to jailbreak…

Artificial Intelligence · Computer Science 2025-01-08 Fengxiang Wang , Ranjie Duan , Peng Xiao , Xiaojun Jia , Shiji Zhao , Cheng Wei , YueFeng Chen , Chongwen Wang , Jialing Tao , Hang Su , Jun Zhu , Hui Xue

Modern LLM agents solve complex tasks by operating in iterative execution loops, where they repeatedly reason, act, and self-evaluate progress to determine when a task is complete. In this work, we show that while this self-directed loop…

Cryptography and Security · Computer Science 2026-05-08 Huiyu Xu , Zhibo Wang , Wenhui Zhang , Ziqi Zhu , Yaopeng Wang , Kui Ren , Chun Chen

We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. Existing AI safety approaches often rely on costly human evaluation…

Computation and Language · Computer Science 2025-10-13 Ali Asad , Stephen Obadinma , Radin Shayanfar , Xiaodan Zhu

Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human…

Computation and Language · Computer Science 2022-02-08 Ethan Perez , Saffron Huang , Francis Song , Trevor Cai , Roman Ring , John Aslanides , Amelia Glaese , Nat McAleese , Geoffrey Irving

Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters, enabling dynamic execution, debugging, and interactive programming capabilities. While these advancements…

Software Engineering · Computer Science 2025-11-12 Chengquan Guo , Chulin Xie , Yu Yang , Zhaorun Chen , Zinan Lin , Xander Davies , Yarin Gal , Dawn Song , Bo Li

In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks predominantly focus on the visual modality, perturbing solely…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Zonghao Ying , Aishan Liu , Tianyuan Zhang , Zhengmin Yu , Siyuan Liang , Xianglong Liu , Dacheng Tao

Automatic code optimization remains a difficult challenge, particularly for complex loop nests on modern hardware. This paper investigates a novel approach to code optimization where Large Language Models (LLMs) guide the process through a…

Programming Languages · Computer Science 2025-12-30 Massinissa Merouani , Islem Kara Bernou , Riyadh Baghdadi

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…

Cryptography and Security · Computer Science 2026-04-16 Yiran Gao , Kim Hammar , Tao Li