🖍️
Pesidious
  • Introduction
  • Pre-requisites
  • Train Models (optional)
  • Mutate Malware
  • HowTo
    • Design your own RL agent
    • Train models against your custom classifier
    • Add more mutations
  • Conclusion
Powered by GitBook
On this page

Was this helpful?

  1. HowTo

Design your own RL agent

PreviousMutate MalwareNextTrain models against your custom classifier

Last updated 4 years ago

Was this helpful?

The malware-score-env and malware-env are available gym environments that you can use to train your own RL agent. 

import gym
import gym_malware

env = gym.make("malware-v0")
env = gym.make("malware-score-v0")
env.seed(args.seed)

The environments are inspired by the endgameinc environments available .

PEsidious has a modified environment that makes use of GAN. The mutations were also added/changed/removed to improve the evasiveness of the malware and maintain functionality by making use of c++.

here