AI · Article
Google Says Attackers Now Use Autonomous Multi-Agent AI Tools in Cyberattacks
지디넷코리아 ·

At a glance
Google's threat intelligence team published its latest AI Threat Tracker report, showing that attackers are using AI more autonomously and at larger scale. The report covers multi-agent attack tools, automated exploitation, stolen AI access, and fake-account influence campaigns. Google said it has blocked misuse of its Gemini service and disabled related accounts.
Key points
- Attackers moved from manual prompting to autonomous multi-agent attack tools that run multi-step intrusions faster.
- AI was used to compare code before and after security patches and quickly build attacks on flaws not yet fixed.
- Criminals stole AI login credentials and cloud resources and resold access to advanced AI models through underground proxy services.
- State-linked groups and influence firms used AI to mass-produce fake media and run over 100,000 fake accounts, and Google disabled the accounts involved.
Why it matters
AI is making cyberattacks faster and less dependent on people, so users and companies need to update systems quickly.
Original source
구글 "해킹 진화...자율형 멀티 에이전트 기승"
지디넷코리아 · Nov 17, 22:22 KST
Read on 지디넷코리아 ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to 지디넷코리아.
Other coverage
Google · Ranking and more news
More from this field
- Google Brings Duplex Calling to Gemini, Letting AI Phone Businesses for You
Google has moved its Duplex phone-calling technology into the Gemini app, so Gemini can now call businesses for you. The system has changed a lot since 2018, shifting from narrow custom models to a single stack built on Gemini.
Google Research blog · Nov 21, 08:30 KST - Google Releases Project Genie, an AI That Generates Explorable Worlds
Google has released Project Genie, an AI tool that creates interactive worlds you can explore. The video shows how to access it, walks through a generated world and a T-Rex demo, and discusses why this early technology matters.
The AI Advantage · Nov 21, 08:21 KST - Anthropic Employee Says Claude Helped Prove Riemann Hypothesis
An Anthropic employee and mathematician, Levent Alpöge, says he used the company's Claude chatbot to create a detailed proof of the Riemann hypothesis over about six weeks. The proof has not yet been checked, and it is over 250,000 lines long in Lean, a computer language used to confirm maths proofs.
BBC News · Nov 21, 08:08 KST - Cole Medin Live-Streams His AI Software Factory Turning Ideas Into Working Software
Cole Medin runs his AI software factory live, taking rough requests from viewers through planning, building, and checking until working software runs on screen. He explains how it works and what he learned building it. The stream also shows a game the system built.
Cole Medin · Nov 21, 08:08 KST