SyzVegas: Beating Kernel Fuzzing Odds with Reinforcement Learning.
Daimeng WangZheng ZhangHang ZhangZhiyun QianSrikanth V. KrishnamurthyNael B. Abu-GhazalehPublished in: USENIX Security Symposium (2021)
Keyphrases
- reinforcement learning
- kernel function
- kernel based learning
- kernel methods
- function approximation
- kernel regression
- support vector
- robot control
- reinforcement learning algorithms
- temporal difference
- learning problems
- kernel machines
- positive definite
- component analysis
- model free
- neural network
- learning algorithm
- markov decision processes
- odds ratio
- sparse kernel
- multi agent
- dynamic programming
- machine learning
- reproducing kernel hilbert space
- multiple kernel learning
- loss function
- optimal policy
- similarity measure