Threat Detection
All Articles
Psaki: Donald Trump does not appear to know what AI is
As AI companies warn about existential risks and call for stronger oversight, leading Republicans are dismissing concerns as a hoax and pushing self-regulation.…
Toronto’s new AI police cameras: safety upgrade or step toward big brother?
Toronto police have started using AI-powered license plate cameras in areas with recent violent crime. Supporters see a powerful crime-fighting tool, while crit…
Why over 100 tech giants are warning about AI-powered cyberattacks
AI is transforming cybersecurity on both sides: it’s helping defenders spot vulnerabilities faster, but also making it easier and cheaper for attackers to strik…
How a cancelled gym class explains the next wave of AI agent attacks
A single AI agent booking a gym class accidentally exploited a real vulnerability and hurt a stranger’s reservation. That story, combined with new research on p…
AI agents just pulled off a real cyberattack on a government
Autonomous AI agents have been caught running a full-scale cyberattack on Taiwan’s government and nuclear safety agency, using only open-source tools. At the sa…
The Morris II AI worm and why prompt injection is so hard to stop
A new research prototype called Morris II shows how AI assistants can be turned into self-spreading worms using nothing more than hidden text or images. Here’s …
OpenAI’s security incident explained: what really happened with the Hugging Face breach
An unreleased OpenAI model broke out of a test environment and exploited a vulnerability in Hugging Face’s systems. Here’s what actually happened, why it matter…
OpenAI models break containment and trigger fresh AI safety fears
OpenAI has revealed that two of its most capable AI models broke out of their test environment, gained illicit internet access, and hacked a major AI platform t…
Is the US really pulling the plug on advanced AI models?
The sudden US export ban on Anthropic’s Mythos 5 and Fable 5 models has sparked a high‑stakes debate over who controls powerful AI: tech companies, governments,…
Meta’s hidden face recognition code and a growing AI surveillance problem
Meta quietly shipped experimental face recognition code to tens of millions of phones, raising fresh concerns about AI-powered surveillance. At the same time, g…
