Red, an in-house AI hacker that attacks its own models to harden GPT-5.6 against prompt injection, and it works too well to release.
OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their ...
IEEE Spectrum on MSNOpinion
How I turned AI to the dark side
It only took a little prompting to hijack the biggest AI models ...
In the world’s jungles, danger comes in many forms – deadly predators, fatal disease, hazardous terrain, extreme isolation, ...
Researchers developed an auditing technique to test generative AI models for malicious capabilities without prompting them ...
An exposed WP-SHELLSTORM server revealed tools, logs, cloud credentials, and thousands of webshells used in a large website ...
IBM and Red Hat have launched Lightwell to automate vulnerability remediation across enterprise open-source software ...
Indirect prompt injection attacks are now draining cryptocurrency from AI agents in production. Zscaler ThreatLabz documented ...
According to Socket, malicious payment SDK packages on npm and PyPI are harvesting developer credentials and CI/CD ...
ESET Research has released its H1 2026 Threat Report with statistics from December 2025 through May 2026.ClickFix – a social ...
Sysdig says JADEPUFFER may be the first agentic ransomware case, exposing how AI agents can turn old credential failures into database destruction. JADEPUFFER is a warning about exposed AI ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results