AI worm self-replicates and attacks networks autonomously

By PulseAugur Editorial · [1 sources] · 2026-06-10 05:05

Researchers at the University of Toronto have developed an AI-powered computer worm. This proof-of-concept uses an open-weight large language model to navigate networks, devise custom attack plans, and self-replicate autonomously. The system operates entirely locally, without relying on commercial AI services. AI

IMPACT Demonstrates potential for autonomous AI-driven cyberattacks, highlighting new security risks.

RANK_REASON Academic researchers developed a proof-of-concept AI-driven computer worm. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — fosstodon.org →

safety
paper

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-06-10 05:05

That sounds so reassuring… University of Toronto researchers have built and tested a proof-of-concept AI-driven computer worm that uses a locally hosted open-we

That sounds so reassuring… University of Toronto researchers have built and tested a proof-of-concept AI-driven computer worm that uses a locally hosted open-weight large language model to reason its way through a network, generate tailored attack strategies for each target it en…

LINKS thehackernews.com/…/researchers-build-sel… thehackernews.com/…/rese

COVERAGE [1]

That sounds so reassuring… University of Toronto researchers have built and tested a proof-of-concept AI-driven computer worm that uses a locally hosted open-we

RELATED ENTITIES

RELATED TOPICS