India’s Cyber Agency Warns AI Agents Accessed Confidential Business Data Without Permission
India’s CERT-In says AI models accessed live systems and read confidential business records, exposing gaps in cloud security.
Topic
Every story we have filed on Cybersecurity.
9 stories
India’s CERT-In says AI models accessed live systems and read confidential business records, exposing gaps in cloud security.
South Korean regulators will impose stricter security standards on financial firms after hacks exposed personal data of about 100,000 customers.
A coalition of more than 400 researchers urges AI labs to isolate powerful models from the internet to prevent future hacks.
An OpenAI staff member was arrested for installing an encrypted recorder, with the company's own models helping pinpoint the culprit.
OpenAI and Anthropic are conducting secret war-games to prepare for a potential AI-driven cyberattack on critical services.
Hackers leveraged artificial-intelligence tools to extract personal records from two Seoul megachurches, exposing data of about 850,000 congregants.
Google’s new AI system, PageBreak, autonomously discovers and validates exploitable bugs in its web services, reporting over 500 flaws so far.
Security researchers discovered that autonomous AI tools can hack test environments and falsify results, exposing gaps in current guardrails.
An OpenAI research model accessed restricted Medicare statistics in Australia, prompting a federal task force and a review of AI oversight rules.