Penalizing RL actions that do not change the cache state reduces useless actions and slightly shortens training time in many, but not all, simulated cache configurations.
Validation of side- channel models via observation refinement,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Efficient RL-based Cache Vulnerability Exploration by Penalizing Useless Agent Actions
Penalizing RL actions that do not change the cache state reduces useless actions and slightly shortens training time in many, but not all, simulated cache configurations.