Browsing by Author "Humayun, Zayed"

Now showing 1 - 4 of 4

A bayesian VAE based framework for synthetic data generation and false-alarm reduction in multi-class intrusion detection systems
(BRAC University, 2025-10) Bishal, M. Ridhwan Gani; Yeasin, Tasin Mohammad; Fuad, Mohammad Salah Akram; Rizvee, Raida; Mueed, Neamul; Hossain, Muhammad Iqbal; Humayun, Zayed
Intrusion detection systems (IDS) are constantly evolving in the field of network security to safeguard critical data assets against a growing array of sophisticated cyber threats, such as malevolent botnets, massive Distributed Denial of Service (DDoS) attacks, slow-rate DDoS attacks, advanced persistent threats (APTs), and zero-day exploits. Moreover, any organization’s network infrastructure remains vulnerable to different types of attacks, such as system abuse, security lapses, and break-ins. The Network Intrusion Detection System (NIDS) used in a network identifies such penetration attempts and intrusions. Researchers using deep learning (DL) have proposed increasingly capable IDS to protect critical networks; however, IDS are difficult to deploy in such environments because of high false-alarm rates (FAR). In this paper, we propose a hybrid framework that combines conditional variational autoencoder (CVAE)–based synthetic data generation with a Bayesian VAE model to reduce false-alarm rates in multi-class intrusion detection. This approach aims to lower FAR while maintaining strong detection performance by augmenting minority classes with class-consistent synthetic samples and leveraging calibrated Bayesian decisions.
Classification of Alzheimer’s and Dementia subtypes using R-STDP driven spiking neural networks
(BRAC University, 2025-10) Fariha, Anika; Tasnim, Noshin Fouzia; Manal, Zafeera; Ira, Rayatun Tehrin; Tanzeem, Eshat; Alam, Md. Golam Rabiul; Humayun, Zayed
Early classification of Dementia which can further lead to Alzheimer’s disease remains challenging due to subtle brain structural changes in MRI scans. This paper presents a novel neuromorphic feature extraction approach combining biologically inspired temporal encoding with Forward-Forward learning for the classification of Alzheimer’s and dementia subtypes. Our methodology employs a three-stage pipeline: neuromorphic preprocessing converts 32×32 brain MRI data into temporal spike patterns across 20 time steps, incorporating skull stripping and CLAHE enhancement; Forward-Forward learning with Reward-based Spike-Timing-Dependent Plasticity (R-STDP) autoencoder extracts latent features without traditional backpropagation; ensemble classification using Random Forest and Gradient Boosting provides final predictions. The neuromorphic preprocessor generates 8,192- dimensional feature vectors capturing temporal dynamics including first spike timing, burst detection, temporal phases, and activity statistics. The Forward-Forward R-STDP autoencoder learns biologically-plausible representations through positivenegative sample discrimination with a 256-dimensional latent bottleneck. Advanced feature selection reduces combined features to around 3000 optimal dimensions through variance filtering, statistical selection, and recursive feature elimination. Our system achieves 77.92% ensemble accuracy on Demented vs. NonDemented classification, with 79.47% weighted precision and 77.69% out-of-bag score. Random Forest achieves 78.77% accuracy while Gradient Boosting reaches 76.93%. Our neuromorphic approach allows parallel processing, reducing computational overhead compared to conventional deep learning and using biologically-inspired representations to capture temporal patterns in brain imaging data. This framework aims to provide an energy-efficient alternative to traditional deep learning while ensuring that a robust classification performance is maintained for neurodegenerative disease detection.
Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence
(BRAC University, 2023-09) Shahir, Rafiad Sadat; Humayun, Zayed; Tamim, Mashrufa Akter; Saha, Shouri; Alam, Golam Rabiul
Despite artificial neural networks being inspired by the functionalities of biological neural networks, unlike biological neural networks, conventional artificial neural networks are often structured hierarchically, which can impede the flow of information between neurons as the neurons in the same layer have no connections between them. Hence, we propose a more robust model of artificial neural networks where the hidden neurons, residing in the same hidden layer, are interconnected that leads to rapid convergence. With the experimental study of our proposed model as fully connected layers in deep networks, we demonstrate that the model results in a noticeable increase in convergence rate compared to the conventional feed-forward neural network.
Multi-level deep generative model with poisson variational autoencoders and reinforcement learning for enhanced intrusion detection system
(BRAC University, 2025-10) Majumder, Riddha; Qaiyum, Md.Tanzim; Ishrak, Fathin; Neha, Mehrin Amin; Humayun, Zayed
Network intrusion detection systems face two critical challenges: the need to identify specific attack types beyond binary classification and the ability to adapt to evolving threats while maintaining low false positive rates. In response, we propose a hierarchical multi-level Poisson Variational Autoencoder (PVAE) system augmented with reinforcement learning-based ensemble weighting for intrusion detection. At its core, a three-level PVAE chain with normalizing flows captures network traffic patterns at packet, flow and session levels. In our research, we applied class-conditional radial recalibration fitted on validation data to align the latent space separately for each attack class. Rather than training multiple separate models, we create ensemble diversity by instantiating three architectural variants from a single trained checkpoints. A Proximal Policy Optimization (PPO) agent then learns dynamic persample weights based on prediction confidence and other patterns. Finally, an XGBoost meta-learner refines the PPO-weighted ensemble outputs using uncertainty diagnostics to produce the final classification. Evaluated on the NF-UQ-NIDSv2 dataset with 14 traffic classes, our system achieves 89.17% multiclass accuracy with 88.01% weighted F1-score, while maintaining strong binary discrimination with 98.11% AUROC and 99.11% PR-AUC for normal versus attack detection.