paper-with-me

홈 › Papers

Anecdoctoring: Automated Red-Teaming Across Language and Place

2025-09-23 · Alejandro Cuevas, Saloni Dash, Bharat Kumar Nayak, Dan Vann, Madeleine I. G. Daepp arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.19143

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Similar Papers 제목 키워드 기반

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

2024-02-06 · Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou 외

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 Teaming

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration

2026-03-24 · Chunxiao Li, Lijun Li, Jing Shao arxiv

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 Teaming

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

2025-12-21 · Zhang Wei, Hanxuan Chen, Peilu Hu, Zhenyuan Wei 외 arxiv

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 Detection

Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models

2025-06-08 · Ren-Jian Wang, Ke Xue, Zeyu Qin, Ziniu Li 외

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-Embedding

PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI

2026-05-07 · Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim, Akshita Jha 외 arxiv

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…