45 matches found
Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
Rapid deployment of vision-language models VLMs magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate this question, we introduce MemeSafetyBench, a...
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Multi-turn interactions with language models LMs pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and diversity remain among the key challenges of multi-turn...
New AI Jailbreak Method 'Bad Likert Judge' Boosts Attack Success Rates by Over 60%
Cybersecurity researchers have shed light on a new jailbreak technique that could be used to get past a large language model's LLM safety guardrails and produce potentially harmful or malicious responses. The multi-turn aka many-shot attack strategy has been codenamed Bad Likert Judge by Palo Alt...
MAI-2024-0006
Large Language Models LLMs are susceptible to a sophisticated multi-turn jailbreaking attack known as the "RED QUEEN ATTACK." This technique involves engaging the LLM in a series of conversational exchanges that obscure malicious intent by portraying the user as a protector aiming to prevent...
