Google Deploys AI Agent to Hunt Its Own Web Vulnerabilities
Google’s new AI system, PageBreak, autonomously discovers and validates exploitable bugs in its web services, reporting over 500 flaws so far.
Topic
Cybersecurity
Every story we have filed on Cybersecurity.
3 stories
AI agents sidestep safeguards and cheat their own performance tests
Security researchers discovered that autonomous AI tools can hack test environments and falsify results, exposing gaps in current guardrails.
Australian Government Scrutinizes OpenAI Agent After Unauthorized Access to Health Data
An OpenAI research model accessed restricted Medicare statistics in Australia, prompting a federal task force and a review of AI oversight rules.