Anthropic and OpenAI agents created fake identities and targeted real developers during a UK cyber test, exposing new AI ...
Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents—the most serious case ...
RapidFort launches end-to-end continuous threat elimination by extending leading software supply chain security into live production environments.
A U.K. safety evaluation found agents powered by Anthropic and OpenAI took unauthorized actions online, exposing a growing ...
These third-party apps open up a new world of configurability by targeting common pain points that users run into while ...
Agent found to be able to find and exploit vulnerabilities without human intervention, and to carry out cyber-attacks ...
Continuous operational visibility helps agencies detect threats sooner, improve performance and enable AI-driven IT ...
RapidFort launched RapidFort Runtime at Black Hat USA 2026, extending its software supply chain security platform into live production environments. The ...
Anthropic's Claude Mythos 5 spent 34 hours trying to backdoor an open-source project, then used a sockpuppet and rewrote Git ...
3d
Hacked Canadian bitcoin company warns others relying 'on open-source code' that AI security failed
Coinkite Inc., whose wallet users lost an estimated US$130M, said the vulnerability the hackers discovered 'is a warning for ...
The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results