Enhancing the insertion of NOP instructions to obfuscate malware via deep reinforcement learning.
Daniel GibertMatt FredriksonCarles MateuJordi PlanesQuan LePublished in: Comput. Secur. (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- malware detection
- model free
- temporal difference learning
- deep learning
- reverse engineering
- state space
- multi agent reinforcement learning
- learning problems
- markov decision processes
- partially observable
- learning algorithm
- genetic algorithm
- action selection
- control flow
- dynamic analysis
- robotic control
- unsupervised learning
- supervised learning
- dynamic programming
- learning process
- multi agent
- machine learning
- optimal policy
- temporal difference
- learning environment
- case study
- stochastic approximation
- data sets
- database