Automated Red Teaming

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 35

All topics

STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming
Apr 21, 2026MinJae Jung, YongTaek Lim, Chaeyun Kim +3LLM Security LLM Jailbreak Attacks
DATUMO INC.
Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
Apr 9, 2026Wenkui Yang, Chao Jin, Haisu Zhu +7GUI Agents AI Agent Security
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · 2MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences · 4ShanghaiTech University +2
Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services
Mar 11, 2026Fabrizio Dimino, Bhaskarjit Sarmah, Stefano PasqualiLanguage Model Safety Evaluation LLM Safety
1Domyn, New York, US · 2Domyn, New York, US · 3Domyn, New York, US
Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models
Dec 21, 2025Zhang Wei, Hanxuan Chen, Peilu Hu +19Adversarial Robustness of Language Models LLM Safety Evaluation
Independent Researcher · Hunan University · Shenzhen Kaihong Digital Industry Development Co., Ltd. +12
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
Jun 25, 2025Wenjie Jacky Mo, Qin Liu, Xiaofei Wen +5Adversarial Prompt Generation LLM Red Teaming
University of California, Davis · University of Southern California

Apr 21, 2026, cs.CLJ/K move · Enter open · S save

STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming

MinJae Jung, YongTaek Lim, Chaeyun Kim, Junghwan Kim+2

DATUMO INC.

LLM Security LLM Jailbreak Attacks Automated Red Teaming

Open paper AskPDF arXiv

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 that effectively generates such prompts. STAR-Teaming integrates a Multi-Agent System (MAS) with a Strategy-Response Multiplex Network and employs network-driven optimization to sample effective attack strategies. This network-based approach recasts the intractable high-dimensional embedding space into a tractable structure, yielding two key advantages: it enhances the interpretability of the LLM's strategic vulnerabilities, and it streamlines the search for effective strategies by organizing the search space into semantic communities, thereby preventing redundant exploration. Empirical results demonstrate that STAR-Teaming significantly surpasses existing methods, achieving a higher attack success rate (ASR) at a lower computational cost. Extensive experiments validate the effectiveness and explainability of the Multiplex Network. The code is available at https://github.com/selectstar-ai/STAR-Teaming-paper.

Momentum

Related topics

Latest papers 35

STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services

Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs