Automating Privilege Escalation with Deep Reinforcement Learning.
Kalle KujanpääWillie VictorAlexander IlinPublished in: AISec@CCS (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- temporal difference
- markov decision processes
- reinforcement learning algorithms
- artificial neural networks
- control problems
- machine learning
- hidden markov models
- optimal policy
- multi agent reinforcement learning
- expert systems
- website
- action selection
- reinforcement learning methods
- learning capabilities
- belief nets
- active exploration
- learning classifier systems
- security policies
- learning problems
- transfer learning
- access control
- control system
- evolutionary algorithm
- learning process
- decision trees
- artificial intelligence