GTIGは、GoogleのAIモデル「Gemini」が今回のエクスプロイトの開発に使われたとは考えていないとした一方、スクリプトに教育的な説明文や幻覚（ハルシネーション）とみられるCVSS（共通脆弱性評価システム）スコア、大規模言語モデル（LLM）の ...

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to ...

Google’s Threat Intelligence Group (GTIG) reported the first confirmed instance of a zero-day exploit created with AI, targeting a two-factor authentication bypass in a widely used open-source system ...

Google said it disrupted what it described as the first known cyberattack in which hackers used artificial intelligence to find and build an exploit for a previously unknown software flaw ...

First AI zero-day: Google identified and disrupted the first documented case of hackers using AI to create and prepare a zero ...

The 2FA bypass exploit stemmed from a faulty trust assumption, providing evidence of AI reasoning that can discover high-level logic flaws. The Google Threat Intelligence Group (GTIG) today released ...