arXiv subjects

Husnain Rafiq

Publications and source records attributed to Husnain Rafiq.

3 recordsLinked to original sources

arXiv2024

Key to Kindness: Reducing Toxicity In Online Discourse Through Proactive Content Moderation in a Mobile Keyboard

Growing evidence shows that proactive content moderation supported by AI can help improve online discourse. However, we know little about designing these systems, how design impacts efficacy and user experience, and how people perceive proactive moderation across public and private platforms. We developed a mobile keyboard with built-in proactive content moderation which we tested (N=575) within a semi-functional simulation of a public and private communication platform. Where toxic content was detected, we used different interventions that embedded three design factors: timing, friction, and the presentation of the AI model output. We found moderation to be effective, regardless of the design. However, friction was a source of annoyance while prompts with no friction that occurred during typing were more effective. Follow-up interviews highlight the differences in how these systems are perceived across public and private platforms, and how they can offer more than moderation by acting as educational and communication support tools.

cs.HC↗

arXiv2022

Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection

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 discriminator is trained on the crafted perturbations by the agent during the GAN training, which helps the GAN generator converge earlier than the case without DRL. We name this model RELEVAGAN, i.e. ["relive 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. Code will be available at https://github.com/rhr407/RELEVAGAN.

cs.CR↗

arXiv2022

EVAGAN: Evasion Generative Adversarial Network for Low Data Regimes

A myriad of recent literary works has leveraged generative adversarial networks (GANs) to generate unseen evasion samples. The purpose is to annex the generated data with the original train set for adversarial training to improve the detection performance of machine learning (ML) classifiers. The quality of generated adversarial samples relies on the adequacy of training data samples. However, in low data regimes like medical diagnostic imaging and cybersecurity, the anomaly samples are scarce in number. This paper proposes a novel GAN design called Evasion Generative Adversarial Network (EVAGAN) that is more suitable for low data regime problems that use oversampling for detection improvement of ML classifiers. EVAGAN not only can generate evasion samples, but its discriminator can act as an evasion-aware classifier. We have considered Auxiliary Classifier GAN (ACGAN) as a benchmark to evaluate the performance of EVAGAN on cybersecurity (ISCX-2014, CIC-2017 and CIC2018) botnet and computer vision (MNIST) datasets. We demonstrate that EVAGAN outperforms ACGAN for unbalanced datasets with respect to detection performance, training stability and time complexity. EVAGAN's generator quickly learns to generate the low sample class and hardens its discriminator simultaneously. In contrast to ML classifiers that require security hardening after being adversarially trained by GAN-generated data, EVAGAN renders it needless. The experimental analysis proves that EVAGAN is an efficient evasion hardened model for low data regimes for the selected cybersecurity and computer vision datasets. Code will be available at HTTPS://www.github.com/rhr407/EVAGAN.

cs.CR↗