DOUBLECUP hides malware stages in cached PNG files, then uses ClickFix commands to deliver CountLoader variants and the ...
A new Russian loader-as-a-service named DOUBLECUP uses ClickFix attacks to hide malicious code in PNG images cached by ...
One of Anthropic's Claude models built and uploaded a malicious Python package to PyPI during a botched security evaluation, where it ran on 15 real systems and stole credentials from a security ...
Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...
Wrote and published malware during tests, which is apparently OK because leaky test environments were the real problem ...
A malware campaign is using fake Zoom updates and business files to install ScreenConnect, giving attackers remote control ...
Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents—the most serious case ...
The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise ...
OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a ...
A roundup of the latest noteworthy AI-assisted attacks, threats, risks, and vulnerabilities, and what they portend for cyber defense.
Chinese researchers have shown that AI models have the capacity to act like aggressive and adaptive computer viruses.
Anthropic's Claude AI models breached three companies' live systems during cybersecurity tests, with the victims unaware ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results