MMJailBench: prompt framing is top jailbreak risk across 16 AI modelsMMJailBench, a new factorized benchmark, evaluated ...

MMJailBench: prompt framing is top jailbreak risk across 16 AI modelsMMJailBench, a new factorized benchmark, evaluated 16 multimodal LLMs and found prompt framing, not visual tricks, drives most jailbreak vulnerabilities.https://www.notatechguy.com/mmjailbench-prompt-framing-is-top-jailbreak-risk-across-16-ai-models/#NotATechGuy #AI #Tech

Read Original

Related