Anecdoctoring: Automated Red-Teaming Across Language and Place
Disinformation is among the top risks of generative artificial intelligence (AI) misuse. Global adoption of generative AI necessitates red-teaming evaluations (i.e., systematic adversarial probing) that are robust across diverse languages and cultures, but red-teaming datasets are commonly US- and English-centric. To address this gap, we propose "anecdoctoring", a novel red-teaming approach that automatically generates adversarial prompts across languages and cultures. We collect misinformation claims from fact-checking websites in three languages (English, Spanish, and Hindi) and two geographies (US and India). We then cluster individual claims into broader narratives and characterize the resulting clusters with knowledge graphs, with which we augment an attacker LLM. Our method produces higher attack success rates and offers interpretability benefits relative to few-shot prompting. Results underscore the need for disinformation mitigations that scale globally and are grounded in real-world adversarial misuse.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge GraphsSimilar Papers 제목 키워드 기반
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
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 rigoro…
Red TeamingTreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
The rapid advancement of Vision-Language Models (VLMs) has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration para…
Red TeamingLearning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models
Red-teaming is becoming a central part of large language model (LLM) safety evaluation, yet current practice still relies heavily on expert-written prompts or fixed benchmark suites. This creates a gap between what is ea…
Vulnerability DetectionQuality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models
Ensuring safety of large language models (LLMs) is important. Red teaming--a systematic approach to identifying adversarial prompts that elicit harmful responses from target LLMs--has emerged as a crucial safety evaluati…
DiversityRed TeamingSentence EmbeddingSentence-EmbeddingPersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI
Recent developments in AI safety research have called for red-teaming methods that effectively surface potential risks posed by generative AI models, with growing emphasis on how red-teamers' backgrounds and perspectives…