Skip to main content

Research Repository

Advanced Search

Deep reinforcement learning based Evasion Generative Adversarial Network for botnet detection

Randhawa, Rizwan Hamid; Aslam, Nauman; Alauthman, Mohammad; Khalid, Muhammad; Rafiq, Husnain

Authors

Rizwan Hamid Randhawa

Nauman Aslam

Mohammad Alauthman

Husnain Rafiq



Abstract

Botnet detectors based on machine learning are potential targets for adversarial evasion attacks. Several research works employ adversarial training with samples generated from generative adversarial nets (GANs) to make the botnet detectors adept at recognising adversarial evasions. However, the synthetic evasions may not follow the original semantics of the input samples. This paper proposes a novel GAN model leveraged with deep reinforcement learning (DRL) to explore semantic aware samples and simultaneously harden its detection. A DRL agent is used to attack the discriminator of the GAN that acts as a botnet detector. The agent trains the discriminator on the crafted perturbations during the GAN training, which helps the GAN generator converge earlier than the case without DRL. We name this model RELEVAGAN, i.e. [“relieve a GAN” or deep REinforcement Learning-based Evasion Generative Adversarial Network] because, with the help of DRL, it minimises the GAN's job by letting its generator explore the evasion samples within the semantic limits. During the GAN training, the attacks are conducted to adjust the discriminator weights for learning crafted perturbations by the agent. RELEVAGAN does not require adversarial training for the ML classifiers since it can act as an adversarial semantic-aware botnet detection model. The code will be available at https://github.com/rhr407/RELEVAGAN.

Citation

Randhawa, R. H., Aslam, N., Alauthman, M., Khalid, M., & Rafiq, H. (2024). Deep reinforcement learning based Evasion Generative Adversarial Network for botnet detection. Future generations computer systems : FGCS, 150, 294-302. https://doi.org/10.1016/j.future.2023.09.011

Journal Article Type Article
Acceptance Date Sep 3, 2023
Online Publication Date Sep 7, 2023
Publication Date Jan 1, 2024
Deposit Date Nov 2, 2023
Publicly Available Date Nov 3, 2023
Journal Future Generation Computer Systems
Print ISSN 0167-739X
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 150
Pages 294-302
DOI https://doi.org/10.1016/j.future.2023.09.011
Keywords Low data regimes; GANs; ACGAN; EVAGAN; Botnet
Public URL https://hull-repository.worktribe.com/output/4430435

Files




You might also like



Downloadable Citations