‘Zoomsday’ hack uncovered using fewer than 20 AI prompts

Read full story on The Verge
Share
‘Zoomsday’ hack uncovered using fewer than 20 AI prompts
AI disclosure

Summary

Zoom has patched a major security vulnerability that could allow an attacker to hijack anyone's device during a meeting. In a blog post on Tuesday, researchers at A Security say they uncovered the flaw using "fewer than 20 prompts on publicly available AI models," as reported earlier by Wired. The exploit involved Zoom's annotation feature, […]

Original reporting

Open original source

Related coverage

Read full article on The Verge

Get the AFBytes Brief

Major stories, AI-assisted analysis, and what to watch next. Free, monthly, unsubscribe anytime.