AutoCAT: Reinforcement Learning for Automated Exploration of Cache Timing-Channel Attacks.
Mulong LuoWenjie XiongGeunbae LeeYueying LiXiaomeng YangAmy ZhangYuandong TianHsien-Hsin S. LeeG. Edward SuhPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- model based reinforcement learning
- multi channel
- exploration exploitation
- semi automated
- function approximation
- main memory
- learning algorithm
- reinforcement learning algorithms
- model free
- countermeasures
- markov decision processes
- temporal difference
- dynamic programming
- autonomous learning
- multi agent
- security threats
- query processing
- watermarking scheme