Self‑Replicating AI Worm Uses Local Open‑Weight Models to Scan CVEs and Propagate

A Toronto‑based CleverHans Lab team demonstrated a self‑replicating AI worm that autonomously scans public CVE advisories, generates exploit strategies with local open‑weight models, gains high‑privilege access, and spreads across 62 % of a 33‑host network without any external API dependencies, prompting new blue‑team defenses.

AI malwareCVE scanningGPU exploitation

0 likes · 10 min read

Self‑Replicating AI Worm Uses Local Open‑Weight Models to Scan CVEs and Propagate

Black & White Path

Mar 20, 2026 · Information Security

When Iran’s Hacker Leaders Were Physically Targeted, a Cross‑Reality Revenge Campaign Unfolded

After the US‑Israel airstrike that killed two senior Iranian cyber‑warfare figures, the Handala group retaliated by hijacking Stryker's Intune system, remotely wiping 200,000 devices, using AI‑generated malware and Starlink connectivity, highlighting the rise of hybrid cyber‑physical warfare.

AI malwareIntune hijackingIran

0 likes · 11 min read

When Iran’s Hacker Leaders Were Physically Targeted, a Cross‑Reality Revenge Campaign Unfolded