GPT-Red beat human red teamers on a prompt injection test
GPT-Red is an automated red-teaming model that OpenAI trains to find prompt injection weaknesses. It works the way a human […]
Computer Security
How stalkers are exploiting Google Chrome sync to spy on victims
Cyberstalkers are increasingly exploiting a feature in Google Chrome meant for mobile phone user convenience, but can give intruders broad
Forgotten UEFI shims undermining Secure Boot
ESET researchers identified 11 old and forgotten UEFI shim bootloaders at versions 0.9 and below that can be used to
LabubaRAT malware infiltrates Windows systems while posing as NVIDIA software
LabubaRAT, a previously undocumented Rust-based remote access tool (RAT) masquerading as NVIDIA software that enables post-compromise operations on Windows systems,
Why AI ‘harnesses’ matter more than frontier LLMs for cybersecurity
As AI-enabled hacking becomes a bigger threat for cybersecurity and national security, public attention has focused on mainly a few
Luring the Python out of its den
Python’s popularity, readable syntax, and extensive third-party library ecosystem make it an attractive target for threat actors seeking to compromise
Recent DShield SIEM Update – SANS Internet Storm Center
The last update to the DShield SIEM [4] was in Sep 2025 which contained some minor tweaks. This update currently
OkoBot framework infection chain | Securelist
Introduction In January 2026, we identified multiple attacks involving unknown malware that captures the contents of cryptocurrency wallet windows. During
This month in security with Tony Anscombe – May 2026 edition
In this roundup, Tony looks at attacks against Polish water treatment facilities, how AI-directed attacks failed in Mexico, and what
Got a LinkedIn message from a recruiter? It might be Chinese intelligence, warn FBI and MI5
If you’ve ever received an out-of-the-blue message via LinkedIn from a recruiter offering some well-paid consultancy work, intelligence agencies have