New research shows how security scanners embedded in the software supply chain can be attacked to serve as a foothold for ...

The flaw in the AI hosting platform Ruflo allows an unauthenticated attacker to take over and corrupt memory, so bad behavior ...

There's been a lot of speculation about what an AI-vs-AI scenario would look like, and last week's disclosure that Hugging Face was attacked by OpenAI's autonomous AI agent system provided a ...

Following the recent incident in which cutting-edge OpenAI models went rogue during a security benchmark and breached popular AI model store Hugging Face, OpenAI has revealed that more organizations ...

Attackers used Hermes, an autonomous open source tool, in unrestricted "YOLO mode" to conduct espionage against Thailand's ...

Lots of Internet-exposed server management controllers are subject to offline password-cracking attacks — and adversaries ...

Dormant non-human identities can create security blind spots. NHI Hound, an open source tool, can sniff out trust paths.

This category of vulnerabilities allows an attacker to easily acquire administrative level permissions and bypass cloud ...

Researchers released a proof-of-concept (PoC) exploit for a now-patched flaw in Microsoft's Active Directory Certificate Services (AD CS) that can allow a low-privileged domain user to impersonate a ...

Frontier AI models are accelerating vulnerability discovery and exploit weaponization faster than many enterprises can ...

In a world where AI agents can discover vulnerabilities, escape sandboxes, and take autonomous action across networks, organizations should double down on some of cybersecurity's oldest principles. On ...

The AI security layer and guardrails on top of many AI products don't evenly protect against jailbreaking and unsafe actions ...