UNBUS: Uncertainty-aware Deep Botnet Detection System in Presence of Perturbed Samples

2022-04-18 · Rahim Taheri

A rising number of botnet families have been successfully detected using deep learning architectures. While the variety of attacks increases, these architectures should become more robust against attacks. They have been proven to be very sensitive to small but well constructed perturbations in the input. Botnet detection requires extremely low false-positive rates (FPR), which are not commonly attainable in contemporary deep learning. Attackers try to increase the FPRs by making poisoned samples. The majority of recent research has focused on the use of model loss functions to build adversarial examples and robust models. In this paper, two LSTM-based classification algorithms for botnet classification with an accuracy higher than 98% are presented. Then, the adversarial attack is proposed, which reduces the accuracy to about 30%. Then, by examining the methods for computing the uncertainty, the defense method is proposed to increase the accuracy to about 70%. By using the deep ensemble and stochastic weight averaging quantification methods it has been investigated the uncertainty of the accuracy in the proposed methods.

📄 PDF Abstract BibTeX arXiv:2204.09502

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Methods 이 논문이 사용한 방법론

Stochastic Weight Averaging Stochastic Weight Averaging is an optimization procedure that averages multiple points along the trajectory of SGD, with a cyclical or…

A Lightweight Federated Learning Approach for Privacy-Preserving Botnet Detection in IoT

2025-10-03 · Taha M. Mahmoud, Naima Kaabouch arxiv

The rapid growth of the Internet of Things (IoT) has expanded opportunities for innovation but also increased exposure to botnet-driven cyberattacks. Conventional detection methods often struggle with scalability, privac…

Intrusion Detection Federated Learning

A Quantized VAE-MLP Botnet Detection Model: A Systematic Evaluation of Quantization-Aware Training and Post-Training Quantization Strategies

2025-11-05 · Hassan Wasswa, Hussein Abbass, Timothy Lynar arxiv

In an effort to counter the increasing IoT botnet-based attacks, state-of-the-art deep learning methods have been proposed and have achieved impressive detection accuracy. However, their computational intensity restricts…

Model Compression

Mobile Botnet Detection: A Deep Learning Approach Using Convolutional Neural Networks

2020-07-01 · Suleiman Y. Yerima, Mohammed K. Alzaylaee

Android, being the most widespread mobile operating systems is increasingly becoming a target for malware. Malicious apps designed to turn mobile devices into bots that may form part of a larger botnet have become quite …

BIG-bench Machine Learning

Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents

2026-03-31 · Haoran Bu, Litian Zhang, Chuxuan Zhang, Zhanyuan Liu 외 arxiv

Driven by large language models (LLMs), social bot can autonomously engage in local interactions, whose human-like behaviors enable them to evade social bot detection. However, while these botnets exhibit realistic local…

Graph Neural Network

Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection

2022-10-06 · Rizwan Hamid Randhawa, Nauman Aslam, Mohammad Alauthman, Muhammad Khalid 외

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 …

Deep Reinforcement Learning Generative Adversarial Network reinforcement-learning Reinforcement Learning+1