safety
fact
bearish
TempJail improves attack success rate over prior state-of-the-art methods by 23.3% under GPT-5.2 evaluation and 22.0% under human evaluation on commercial models
Experiments on closed-source commercial models, including Kling, Seedance, Veo and PixVerse, show that TempJail improves attack success rate over prior state-of-the-art methods by 23.3\% under GPT-5.2 evaluation and 22.0\% under human evaluation.
Computer Vision29 Aug 2026