ProRLearn: boosting prompt tuning-based vulnerability detection by reinforcement learning.
Zilong RenXiaolin JuXiang ChenHao ShenPublished in: Autom. Softw. Eng. (2024)
Keyphrases
- reinforcement learning
- false alarms
- detection algorithm
- detection method
- learning algorithm
- state space
- automatic detection
- object detection
- anomaly detection
- function approximation
- markov decision processes
- false positives
- detection accuracy
- transfer learning
- machine learning
- optimal policy
- ensemble learning
- learning process
- feature selection
- risk assessment
- weak classifiers
- fine tuning