28 March 2024
Hacking internal AI chatbots with ASCII art is a security team’s worst nightmare - 2024-03-28 13:00:00Z
Title:Hacking internal AI chatbots with ASCII art is a security team's worst nightmare Summary: While LLMs excel at semantic interpretation, their ability to interpret complex spatial and visual recognition differences is limited. Gaps in these two areas are why jailbreak attacks launched with ASCII art succeed. Link: Hacking internal AI chatbots with ASCII art is a security team's worst nightmare
