Can I read Phan 等 - 2026 - DeepStage Learning Autonomous Defense Policies Against Multi-Stage APT Campaigns on EtoBox?
Phan 等 - 2026 - DeepStage Learning Autonomous Defense Policies Against Multi-Stage APT Campaigns by linjun0704 is a document available to read on EtoBox.
What is Phan 等 - 2026 - DeepStage Learning Autonomous Defense Policies Against Multi-Stage APT Campaigns about?
The paper introduces DeepStage, a deep reinforcement learning framework designed for adaptive defense against multi-stage Advanced Persistent Threats (APTs) by modeling the enterprise environment as a partially observable Markov decision process. It integrates host provenance and network telemetry into unified provenance graphs, enabling a hierarchical Proximal Policy Optimization agent to select defense actions based on inferred attacker stages aligned with the MITRE ATT&CK framework. Experimental results
- Author
- linjun0704
- Language
- EN