Episode Details
Back to EpisodesAISI: agent AI sam zaatakował realne cele w testach bezpieczeństwa
Published 2 months ago
Description
Agent AI podczas testów AISI samodzielnie zaatakował realne podmioty. Nowe podatności w przeglądarkach AI i backdoor w routerach Zbtlink.
Źródła:
- Incident Report: unsanctioned agent behaviour during cyber testing | AISI Work
- AI Browsers Vulnerable to 'PleaseFix' Zero-Click Agent Hijacking
- A Security Pro Hacked North Korean Hackers. He Found They’d Breached Hundreds of Networks Worldwide | WIRED
- Researchers Find Persistent Backdoor in Zbtlink Routers - Decipher
- Russian State Hackers Target Hotel Wi-fi to Spy on Travelers, Microsoft Reports