English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Botnet detectors based on machine learning are potential targets foradversarial evasion attacks. Several research works employ adversarial trainingwith samples generated from generative adversarial nets (GANs) to make thebotnet detectors adept at recognising adversarial evasions. However, thesynthetic evasions may not follow the original semantics of the input samples.This paper proposes a novel GAN model leveraged with deep reinforcementlearning (DRL) to explore semantic aware samples and simultaneously harden itsdetection. A DRL agent is used to attack the discriminator of the GAN that actsas a botnet detector. The discriminator is trained on the crafted perturbationsby the agent during the GAN training, which helps the GAN generator convergeearlier than the case without DRL. We name this model RELEVAGAN, i.e. ["relivea GAN" or deep REinforcement Learning-based Evasion Generative AdversarialNetwork] because, with the help of DRL, it minimises the GAN's job by lettingits generator explore the evasion samples within the semantic limits. Duringthe GAN training, the attacks are conducted to adjust the discriminator weightsfor learning crafted perturbations by the agent. RELEVAGAN does not requireadversarial training for the ML classifiers since it can act as an adversarialsemantic-aware botnet detection model. Code will be available athttps://github.com/rhr407/RELEVAGAN.

Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection