Skip to content
TodayPrism
Updated 1h agoTech & Cyber

Researchers Use AI Tools To Exploit Vulnerabilities In OpenAI Systems

Headline by Prism · from 1 report

Three Indian-origin researchers successfully identified and exploited security vulnerabilities in OpenAI's systems using AI tools including Claude.

1 outlet · 1 report · EnglishOne source so far

The record

Written from the 1 report below. Nothing here is unsourced.

  • Cybersecurity researchers Mohan Pedhapati, Harsh Jaiswal, and Rahul Maini leveraged artificial intelligence, including Anthropic's Claude, to discover and demonstrate security flaws within OpenAI's infrastructure.
  • The process reportedly took under 72 hours to complete.
  • This incident highlights the growing role of AI in both defensive and offensive security research.

Coverage1

1 report
English national1

All filed from India

Named India · United States · OpenAI · Anthropic · Harsh Jaiswal · Mohan Pedhapati · Rahul Maini

Ask this story

Answers cite the reports above, or say they can't.

← Today’s record

Researchers Use AI Tools To Exploit Vulnerabilities In OpenAI Systems | Prism