{"ID":2858908,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07239","arxiv_id":"2510.07239","title":"Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts","abstract":"Automated red-teaming has emerged as a scalable approach for auditing Large Language Models (LLMs) prior to deployment, yet existing approaches lack mechanisms to efficiently adapt to model-specific vulnerabilities at inference. We introduce Red-Bandit, a red-teaming framework that adapts online to identify and exploit model failure modes under distinct attack styles (e.g., manipulation, slang). Red-Bandit post-trains a set of parameter-efficient LoRA experts, each specialized for a particular attack style, using reinforcement learning that rewards the generation of unsafe prompts via a rule-based safety model. At inference, a multi-armed bandit policy dynamically selects among these attack-style experts based on the target model's response safety, balancing exploration and exploitation. Red-Bandit achieves state-of-the-art results on AdvBench under sufficient exploration (ASR@10), while producing more human-readable prompts (lower perplexity). Moreover, Red-Bandit's bandit policy serves as a diagnostic tool for uncovering model-specific vulnerabilities by indicating which attack styles most effectively elicit unsafe behaviors.","short_abstract":"Automated red-teaming has emerged as a scalable approach for auditing Large Language Models (LLMs) prior to deployment, yet existing approaches lack mechanisms to efficiently adapt to model-specific vulnerabilities at inference. We introduce Red-Bandit, a red-teaming framework that adapts online to identify and exploit...","url_abs":"https://arxiv.org/abs/2510.07239","url_pdf":"https://arxiv.org/pdf/2510.07239v2","authors":"[\"Christos Ziakas\",\"Nicholas Loo\",\"Nishita Jain\",\"Alessandra Russo\"]","published":"2025-10-08T17:06:20Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}