English
Related papers

Related papers: AJAR: Adaptive Jailbreak Architecture for Red-team…

200 papers

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

Artificial Intelligence · Computer Science 2026-05-20 Qiqi Liu , Thorsten Holz , Shilin Ye , Runhan Song

Large language models (LLMs) are widely used in real-world applications, raising concerns about their safety and trustworthiness. While red-teaming with jailbreak prompts exposes the vulnerabilities of LLMs, current efforts focus primarily…

Computation and Language · Computer Science 2025-11-14 Yi Zhao , Youzhi Zhang

For safety reasons, large language models (LLMs) are trained to refuse harmful user instructions, such as assisting dangerous activities. We study an open question in this work: does the desired safety refusal, typically enforced in chat…

Intrusion Detection and Prevention Systems (IDS/IPS) in large enterprises can generate hundreds of thousands of alerts per hour, overwhelming analysts with logs requiring rapidly evolving expertise. Conventional machine-learning detectors…

Cryptography and Security · Computer Science 2026-02-10 Francesco Blefari , Cristian Cosentino , Francesco Aurelio Pironti , Angelo Furfaro , Fabrizio Marozzo

We introduce LLMStinger, a novel approach that leverages Large Language Models (LLMs) to automatically generate adversarial suffixes for jailbreak attacks. Unlike traditional methods, which require complex prompt engineering or white-box…

Machine Learning · Computer Science 2026-01-29 Piyush Jha , Arnav Arora , Vijay Ganesh

Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial ``jailbreak'' attacks designed to bypass safety guardrails. Current safety alignment methods depend heavily on static external red…

Cryptography and Security · Computer Science 2026-01-16 Hao Wang , Yanting Wang , Hao Li , Rui Li , Lei Sha

Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine learning and AI safety, safeguard red teaming has…

Cryptography and Security · Computer Science 2025-06-10 Zifan Wang , Christina Q. Knight , Jeremy Kritz , Willow E. Primack , Julian Michael

Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction settings, where attackers strategically adapt their prompts across conversation turns and pose a…

Machine Learning · Computer Science 2026-03-10 Ruohao Guo , Afshin Oroojlooy , Roshan Sridhar , Miguel Ballesteros , Alan Ritter , Dan Roth

Despite explicit alignment efforts for large language models (LLMs), they can still be exploited to trigger unintended behaviors, a phenomenon known as "jailbreaking." Current jailbreak attack methods mainly focus on discrete prompt…

Cryptography and Security · Computer Science 2025-02-18 Guanghao Zhou , Panjia Qiu , Mingyuan Fan , Cen Chen , Mingyuan Chu , Xin Zhang , Jun Zhou

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

Cryptography and Security · Computer Science 2026-04-08 Zenghao Duan , Yuxin Tian , Zhiyi Yin , Liang Pang , Jingcheng Deng , Zihao Wei , Shicheng Xu , Yuyao Ge , Xueqi Cheng

The integration of Large Language Models (LLMs) into cybersecurity education for criminal justice professionals is currently hindered by the "statelessness" of reactive chatbots and the risk of hallucinations in high-stakes legal contexts.…

Human-Computer Interaction · Computer Science 2026-03-20 Baiqiang Wang , Yan Bai , Juan Li

Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigorously assess new…

This paper introduces Jailbreak-Zero, a novel red teaming methodology that shifts the paradigm of Large Language Model (LLM) safety evaluation from a constrained example-based approach to a more expansive and effective policy-based…

Computation and Language · Computer Science 2026-01-08 Kai Hu , Abhinav Aggarwal , Mehran Khodabandeh , David Zhang , Eric Hsin , Li Chen , Ankit Jain , Matt Fredrikson , Akash Bharadwaj

Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de facto mode of interaction with LLMs for completing long and complex tasks. While LLM capabilities…

Cryptography and Security · Computer Science 2025-10-23 Neeladri Bhuiya , Madhav Aggarwal , Diptanshu Purwar

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt…

Machine Learning · Computer Science 2025-10-07 Taeyoung Yun , Pierre-Luc St-Charles , Jinkyoo Park , Yoshua Bengio , Minsu Kim

The widespread application of large VLMs makes ensuring their secure deployment critical. While recent studies have demonstrated jailbreak attacks on VLMs, existing approaches are limited: they require either white-box access, restricting…

Cryptography and Security · Computer Science 2025-11-11 Yuxuan Zhou , Yang Bai , Kuofeng Gao , Tao Dai , Shu-Tao Xia

Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces…

Cryptography and Security · Computer Science 2025-11-19 Peiran Wang , Yang Liu , Yunfei Lu , Yifeng Cai , Hongbo Chen , Qingyou Yang , Jie Zhang , Jue Hong , Ye Wu

Large Language Models (LLMs) remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a feedback-driven Simulator for iterative query refinement;…

Cryptography and Security · Computer Science 2025-10-22 Sidhant Narula , Javad Rafiei Asl , Mohammad Ghasemigol , Eduardo Blanco , Daniel Takabi

Safety alignment in large language models (LLMs) is increasingly compromised by jailbreak attacks, which can manipulate these models to generate harmful or unintended content. Investigating these attacks is crucial for uncovering model…

Cryptography and Security · Computer Science 2025-05-26 Linbao Li , Yannan Liu , Daojing He , Yu Li

Recent advances in large language model assistants have made them indispensable, raising significant concerns over managing their safety. Automated red teaming offers a promising alternative to the labor-intensive and error-prone manual…

Machine Learning · Computer Science 2024-12-23 Andrew Zhao , Quentin Xu , Matthieu Lin , Shenzhi Wang , Yong-jin Liu , Zilong Zheng , Gao Huang