State-backed hackers are using Google's Gemini AI model to support all stages of an attack, from reconnaissance to post-compromise actions. Bad actors from China (APT31, Temp.HEX), Iran (APT42), North ...

Google detected and blocked a campaign involving more than 100,000 prompts that it claimed were designed to copy the proprietary reasoning capabilities of its Gemini AI model, according to a quarterly ...

Many government-backed cyber threat actors now use AI throughout the attack lifecycle, especially for reconnaissance and social engineering, a new Google study found. In a report published on February ...

According to Google Threat Intelligence, AI has shifted from a simple tool to a primary cybersecurity target. Attackers are now using “distillation” attacks to reverse-engineer proprietary models ...