By tracking per-host ground-truth states, the authors measure how often each CAGE Challenge 2 action actually changes a host's state, finding that top agents waste many actions and that decoys correlate with fewer successful privileged exploits.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Interpreting Agent Behaviors in Reinforcement-Learning-Based Cyber-Battle Simulation Platforms
By tracking per-host ground-truth states, the authors measure how often each CAGE Challenge 2 action actually changes a host's state, finding that top agents waste many actions and that decoys correlate with fewer successful privileged exploits.