~/tag/agentic-attacks

#agentic attacks

2 articles tagged agentic attacks

ARTEX Up Close: Installing, Running, and Hunting a Multi-Agent AI Pentest Framework

ARTEX is an open-source, multi-agent LLM framework that runs real pentest tools with a model choosing the next step. Where to get it now that the original is gone, how to install and configure it safely in a lab, how a task actually runs, where it falls down, how it helps teams, and how to detect and slow down AI-driven attacks.

Aamir LakhaniNov 6, 202624 min read

Adversarial AI

The Uncensored AI Underground: When Attackers Stop Jailbreaking Models and Start Owning Them

Why would an attacker jailbreak a commercial model when they can download an open-weight one, abliterate its refusals, and run it on their own hardware? Abliterated DeepSeek variants, the ten-hour Unit 42 intrusion, CLOSEDQUORUM's LLM voting implant, malware that may carry its own model, vetted cyber access programs, and how defenders should hunt for offensive AI.

Aamir LakhaniNov 6, 202622 min read