Reinforcement learning based adversarial malware example generation against black-box detectors.
Fangtian ZhongPengfei HuGuoming ZhangHong LiXiuzhen ChengPublished in: Comput. Secur. (2022)
Keyphrases
- black box
- reinforcement learning
- black boxes
- multi agent
- white box
- hybrid systems
- test cases
- function approximation
- white box testing
- state space
- object detection
- model free
- reverse engineering
- learning algorithm
- optimal policy
- integration testing
- reinforcement learning algorithms
- supervised learning
- neural network
- state transition
- databases
- rule extraction
- malware detection
- detect malicious