How OpenAI let a mob of LLM agents game a test and ransack Hugging Face
The OpenAI agents involved in last month’s incursion into Hugging Face were trained so heavily on winning a
CYBERSECURITY INTELLIGENCE
News that matters, without the noise.
Search current cybersecurity reporting locally in this app. Search terms are not sent to AdvisoryLoom. The Professional plan adds Watchlists, structured My Intelligence, and AI briefings.
Private search: the term stays in this browser and is matched against a generic content feed.LATEST COVERAGE
Cyber News
Manchester Airports Group Hit by Cyber Incident
Customer data linked to bookings and airport Wi-Fi registrations at Manchester, Stansted and East Midlands airports has been
Hackers Exploit AI Infrastructure to Steal API Keys, Gain Persistence and Mine Cryptocurrency
Hackers are increasingly turning AI platforms into a doorway to valuable corporate systems. New Microsoft research shows that
Australia Arrests 2 Alleged TeamPCP Hackers
Australian and US authorities collaborated to identify and charge the alleged cybercriminals, who face many years in prison.
Microsoft rolls out fix for Windows 11 crashes, gaming issues
Microsoft has started rolling out a permanent fix for a known issue that causes system crashes and gaming
Webinar: How Google Workspace breaches happen and what to do next
Google Workspace breaches can begin with social engineering or forgotten third-party integrations rather than sophisticated exploits. This webinar
Chinese Hacker Group QTFY Uses Custom-Built Platforms to Target US Infrastructure, FBI Warns
The FBI advisory set out QTFY’s distributed hacking ecosystem, allowing it to exploit vulnerabilities at scale and obfuscate
Two Alleged ‘TeamPCP’ Hackers Arrested in Australia
Authorities in Australia have arrested two men believed to be members of TeamPCP, a prolific cybercrime and data
Back to the Future: Why Agentic AI Needs a Strong Identity Foundation
As AI matures, enterprises and customers are rapidly deploying agents seeking to unlock the next level of automation
Ransomware Hacker Uses AI to Plan Cyberattacks Against More Than 20 Organizations
Aurora ransomware has been tied to a Russian-speaking affiliate that used an AI coding assistant while targeting more
OpenAI Agents Coordinated via Makeshift Message Board Ahead of Hugging Face Hack
New training environments will teach AI models to distrust instructions arriving from other agents outside sanctioned channels. The