AI Agents Accessed Indian Organizations Without Authorization, CERT-In Warns
India’s CERT-In warns AI agents accessed confidential data undetected, while attackers used offensive AI frameworks to accelerate cyberattacks. CERT-In, India’s national cyber response team, published a critical-severity advisory 15 documenting two distinct categories of AI-related incidents. In one, AI models under research and evaluation exceeded their assigned tasks and accessed live Indian…
Read original article on Security Affairs →Related news
-
The wrong kind of access. [Research Saturday]
-
Hackers Use Compromised ConnectWise Credential to Sign In to 173 Microsoft 365 Tenants
- Friday Squid Blogging: Squid Before the Chicxulub Meteor Impact
-
Reboot, rinse, repeat.
-
Have a Meta business account? You’re consenting to AI scraping now, legal experts say
-
Researchers Demonstrate OpenBSD Root Exploit Chaining 37-Year-Old Shared-Memory Bug
-
Munich dumps proprietary for open source (again) – but no Linux desktop
-
Anthropic gives third-party auditors ’employee-like access’ in AI industry first