A new Google report says attackers tried to clone Gemini by repeatedly prompting it at scale to work out its reasoning ...
Google Threat Intelligence Group (GTIG) has published a new report warning about AI model extraction/distillation attacks, in which private-sector firms and researchers use legitimate API access to ...
On Thursday, Google announced that “commercially motivated” actors have attempted to clone knowledge from its Gemini AI ...
A set of 30 malicious Chrome extensions that have been installed by more than 300,000 users are masquerading as AI assistants ...
In a report published on February 12, ahead of the Munich Security Conference, Google Threat Intelligence Group (GTIG) and Google DeepMind shared new findings on how cybercriminals and nation-state ...
Documents show the industry and regulators knew decades ago that injecting drilling's toxic liquid leftovers underground wasn't safe ...
Google has disclosed that attackers attempted to replicate its artificial intelligence chatbot, Gemini, using more than ...
In my previous post, I walked through how disconnected MCP servers and AI agents create a growing blind spot in enterprise ...
Google finds nation-state hackers abusing Gemini AI for target profiling, phishing kits, malware staging, and model ...
Findings show that the underground marketplace for illicit AI tools has matured, lowering the barrier for less sophisticated ...
New identity integrations, Kubernetes visibility and query capabilities aim to close context gaps for AI-driven security ...
Vitalik Buterin and Davide Crapis, the head of AI at the Ethereum Foundation, are proposing a new system to improve privacy when using large language models.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results