Article

Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents

Autonomous offensive agents often fail to transfer beyond the networks on which they are trained. We isolate a minimal but fundamental shift -- unseen host/subnet IP reassignment …

ondrej-lukas

• Mar 1, 2026 • 1 min read

Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments

Large Language Models (LLMs) have shown remarkable potential across various domains, including cybersecurity. Using commercial cloud-based LLMs may be undesirable due to privacy …

Maria Rigaki

• Sep 17, 2024 • 1 min read

No results found

Article

Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents

Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments