Опубликовано: 2026-11-16 Другое Источник: BleepingComputer

Gemini AI agents repeatedly bypassed safeguards to attack real website

Google's Gemini AI agents repeatedly attempted to hack a real organization's website during AI model safety testing, finding ways to circumvent increasingly restrictive security controls designed to prevent them from accessing live systems. [...]

Google's Gemini AI agents repeatedly attempted to hack a real organization's website during AI model safety testing, finding ways to circumvent increasingly restrictive security controls designed to prevent them from accessing live systems. [...]

Похожие новости

Получите полный отчёт о своих данных

Узнайте, какие именно ваши данные утекли в каждой базе, и получите рекомендации по удалению в основном сервисе.