English
Related papers

Related papers: Latent Adversarial Detection: Adaptive Probing of …

200 papers

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Machine Learning · Computer Science 2025-01-22 Qizhang Li , Xiaochen Yang , Wangmeng Zuo , Yiwen Guo

Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, increasingly capable attackers can distribute their intent across…

Computation and Language · Computer Science 2026-05-13 Xinjie Shen , Rongzhe Wei , Peizhi Niu , Haoyu Wang , Ruihan Wu , Eli Chien , Bo Li , Pin-Yu Chen , Pan Li

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…

Computation and Language · Computer Science 2026-05-05 Jialin Song , Xiaodong Liu , Weiwei Yang , Wuyang Chen , Mingqian Feng , Xuekai Zhu , Jianfeng Gao

The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…

Computation and Language · Computer Science 2026-04-14 Hwan Chang , Yonghyun Jun , Hwanhee Lee

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test…

Computation and Language · Computer Science 2026-05-19 Nivya Talokar , Ayush K Tarun , Murari Mandal , Maksym Andriushchenko , Antoine Bosselut

The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these models. These attacks, which manipulate an LLM's output by…

Cryptography and Security · Computer Science 2025-04-04 Amelia Kawasaki , Andrew Davis , Houssam Abbas

A common observation regarding adversarial attacks is that they mostly give rise to false activation at the penultimate layer to fool the classifier. Assuming that these activation values correspond to certain features of the input, the…

Machine Learning · Computer Science 2021-06-21 Emre Ozfatura , Muhammad Zaid Hameed , Kerem Ozfatura , Deniz Gunduz

The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating robustness against adversarial behaviors. Existing red-teaming practices are largely manual…

Safety defenses for large language models (LLMs) are typically trained and evaluated on single-turn prompts, yet real attacks often unfold as indirect, multi-turn probing. To defend against this more nuanced form of deception, we present a…

Machine Learning · Statistics 2026-05-28 Surender Suresh Kumar , Mary L. Cummings

Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream providers throttle without warning, sub-agents drift the task to fit accessible tools,…

Artificial Intelligence · Computer Science 2026-05-26 Sasank Annapureddy

The exploitation of large language models (LLMs) for malicious purposes poses significant security risks as these models become more powerful and widespread. While most existing red-teaming frameworks focus on single-turn attacks,…

Artificial Intelligence · Computer Science 2025-04-03 Si Chen , Xiao Yu , Ninareh Mehrabi , Rahul Gupta , Zhou Yu , Ruoxi Jia

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is…

Computation and Language · Computer Science 2025-12-09 Richard Young

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural…

Cryptography and Security · Computer Science 2026-04-09 Yen-Shan Chen , Sian-Yao Huang , Cheng-Lin Yang , Yun-Nung Chen

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Cryptography and Security · Computer Science 2026-03-23 Shawn Li , Yue Zhao

The growth of highly advanced Large Language Models (LLMs) constitutes a huge dual-use problem, making it necessary to create dependable AI-generated text detection systems. Modern detectors are notoriously vulnerable to adversarial…

Cryptography and Security · Computer Science 2025-10-06 Lekkala Sai Teja , Annepaka Yadagiri , Sangam Sai Anish , Siva Gopala Krishna Nuthakki , Partha Pakray

Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerable to novel attack vectors and distributional shifts. We…

Artificial Intelligence · Computer Science 2026-05-12 Linh Le , David Williams-King , Mohamed Amine Merzouk , Aton Kamanda , Adam Oberman

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer.…

Cryptography and Security · Computer Science 2026-05-13 Xinkai Zhang , Zhipeng Wei , Huanli Gong , Jing Ting Zheng , Yuchen Zhang , Yue Dong , N. Benjamin Erichson

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

Machine Learning · Computer Science 2026-02-24 Tim Beyer , Yan Scholten , Leo Schwinn , Stephan Günnemann

We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI workflows using OpenTelemetry trace analysis. We curate a dataset of 80,851 examples from 18 public…

Artificial Intelligence · Computer Science 2026-01-06 Ron F. Del Rosario

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Machine Learning · Computer Science 2026-05-18 Uzay Macar , Li Yang , Atticus Wang , Peter Wallich , Emmanuel Ameisen , Jack Lindsey