Safety · The Verge ·

‘Zoomsday’ hack uncovered using fewer than 20 AI prompts

‘Zoomsday’ hack uncovered using fewer than 20 AI prompts

Zoom patched a vulnerability that could let attackers hijack a participant’s device during a meeting through its annotation feature. Researchers said they found the exploit using fewer than 20 prompts on publicly available AI models.

Read the full story at The Verge →