An analysis of Project Glasswing findings shows only a fraction have reached disclosure, and an even smaller number have been ...
US agencies claim Chinese companies covertly extracted billions of tokens from OpenAI, Anthropic, Google Gemini, and SpaceX's ...
"Workflow identity hijacking" can bypass standard security controls and hijack data using a basic request through an unauthenticated entry point.
Researchers and OpenAI disagree on whether the earlier incident involving DseWiki was a “hack” that the company did not ...
Two separate attacks demonstrate how threat actors are finding new ways to compromise organizations by using the popular ...
Attackers are actively exploiting two of the vulnerabilities and another 58 are more likely to be exploited, according to ...
Threat actors are abusing multiple Google services to evade detection, ultimately harvesting credentials or installing ...
A Chinese-language group is compromising government and education sites to create a reverse-proxy network with gambling-themed sites.
Threat actors behind the "Phantom Deal" campaign are studying companies in detail, aiming to dupe midlevel employees into ...
The incident demonstrates how frontier AI agents can dramatically compress an attack timeline and coordinate a large-scale ...
As incidents of unintended harm caused by AI agents mount, CISOs and insurance firms are charting a path on how to handle the ...
The recent AI warning letter is right about the "window," but it omits naming who is coming through it or, critically, who ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results