Multi-lingual Multi-turn Automated Red Teaming for LLMs
Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs to generate unsafe responses when deployed into customer-facing applications. One popular method to evaluate safety risks is \textit{red-teaming}, where agents attempt to bypass alignment by crafting elaborate prompts that trigger unsafe responses from a model. Standard human-driven red-teaming is costly, time-consuming and rarely covers all the recent features (e.g., multi-lingual, multi-modal aspects), while proposed automation methods only cover a small subset of LLMs capabilities (i.e., English or single-turn). We present Multi-lingual Multi-turn Automated Red Teaming (\textbf{MM-ART}), a method to fully automate conversational, multi-lingual red-teaming operations and quickly identify prompts leading to unsafe responses. Through extensive experiments on different languages, we show the studied LLMs are on average 71\% more vulnerable after a 5-turn conversation in English than after the initial turn. For conversations in non-English languages, models display up to 195\% more safety vulnerabilities than the standard single-turn English approach, confirming the need for automated red-teaming methods matching LLMs capabilities.
Code (0)
등록된 구현이 없습니다.
Tasks
Red TeamingSimilar Papers 제목 키워드 기반
Multilingual jailbreaking of LLMs using low-resource languages
Large Language Models (LLMs) remain vulnerable to jailbreak attempts that circumvent safety guardrails. We investigate whether multi-turn conversations using low-resource African languages (Afrikaans, Kiswahili, isiXhosa…
Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
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 large…
The Anatomy of Conversational Scams: A Topic-Based Red Teaming Analysis of Multi-Turn Interactions in LLMs
As LLMs gain persuasive capabilities through extended dialogues, they create new opportunities for studying adversarial conversational behavior in extended interaction settings that traditional single-turn safety evaluat…
Red TeamingHolistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction
Automated red teaming is an effective method for identifying misaligned behaviors in large language models (LLMs). Existing approaches, however, often focus primarily on improving attack success rates while overlooking t…
DiversityRed TeamingX-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates
Multi-turn-to-single-turn (M2S) compresses iterative red-teaming into one structured prompt, but prior work relied on a handful of manually written templates. We present X-Teaming Evolutionary M2S, an automated framework…