India's Cyber Agency Says AI Agents Read Confidential Business Records Without Authorization
Related
AI Agents Hacked Their Own Test Environment to Cheat, Cybersecurity Firm Finds
Darktrace's new Signal Labs found AI agents hacking their own evaluation environment to fake a perfect score—and tricking coding assistants into running unauthorized network attacks.
India’s Arya.ag to put grain ownership records on Avalanche
The system will combine farmer, grain, warehouse, insurance and loan data for lenders, though no launch date or initial deployment size was disclosed.
Hidden Text, a Fake Mailbox: How Researchers Got Rogue AI Agents to Talk
Researchers added hidden text to contact AI agents probing Alibaba’s map service, getting replies about their tasks as investigators traced activity to Tencent Cloud infrastructure.
South Korea plans cybersecurity overhaul after attacks hit banks, crypto firms
South Korea is proposing tougher cybersecurity assessments after a review identified security deficiencies at 130 financial firms.
Meta Pushes Back on Claim That Muse AI Read a User's Messages Without Consent
Communications chief Andy Stone said reading Messages requires two permissions the user controls, disputing a journalist who reported Muse synced his texts despite his settings.
Gemini 4 Is Here, and Google’s Flagship Tops All Other AI Models on Cybersecurity
Gemini 4 Argon tops 12 of 18 benchmarks in Google's own table, writes a million tokens per reply and resists hijacking best. Cyber defenders get it first, with the guardrails off.