TempJail: Subtitle-based jailbreak attacks on video LVLMs
New arXiv paper introduces TempJail, a temporal jailbreak attack that exploits subtitle scheduling to bypass safety in video large vision-language models. It highlights a largely unexplored attack surface beyond text and image jailbreaks.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Enterprise AI agents limited by messy documents
- Seinfeld AI video shows George in GTA 6 using Minimax H3
- Claude Code adds unrequested corrections to spec
- Ethan Mollick: AI impact research must address older-model limits
- Hobbyist trains 1.2B game music generator on single H100