The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
Attack Path Discovery for Industrial Control System Based on Knowledge-Enhanced Attack Graphs and Causal-Aware Reinforcement Learning
- Published
- Record updated
Summary
Researchers propose an attack path discovery method for industrial control systems that combines knowledge-enhanced attack graphs with causal-aware reinforcement learning. The graphs use the MITRE ATT&CK for ICS matrix to generate attack templates, and causal graphs guide weight assignment and policy updates. Experiments on a fluid catalytic cracking simulation platform and two public datasets show the method increases discovered attack paths by 6.65%, 15.50%, and 11.80% over other methods.