Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Biprodip Pal has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DFedDG2: Distribution-Guided Gossip-Based Generalizable and Communication-Efficient Decentralized Federated Learning

    by Biprodip Pal, Stano Funiak, Jiajun Liu, Peyman Moghadam, Saiful Islam, Alan Wee-Chung Liew

    Traditional federated learning (FL) focuses on collaborative global model training while ensuring privacy and personalization. Decentralized FL (DFL), a variant of FL, allows clients to independently manage and optimize local models without a central server. DFL reduces centralized communication bottlenecks and vulnerability to server failures or attacks. However, because the optimization dynamics change and there is no global model, generalization can suffer, making effective learning under data and model heterogeneity a critical challenge in DFL. Despite growing interest in DFL, the lack of distributional and uncertainty modeling in the literature limits reliability and effective generalization in nonidentically distributed (IID) settings. In this work, we propose DFedDG2, a personalized FL framework that operates within a peer-to-peer protocol. DFedDG2 offers the technical advantage of modeling each client’s local data distribution and exchanging this information with one-hop neighbors. In the decentralized network, clients perform distribution-aware gossip, where statistically similar clients exert greater influence to drive global alignment. This likelihood-weighted mixing fuses only a handful of vectors and scalars, significantly reducing communication costs while aligning semantic spaces across the network and enabling personalized training at the edge. In addition, theoretically, we prove that DFedDG2 achieves a sublinear convergence rate while the consensus error decays at a geometric rate under well-principled properties of gossip. Unlike the label-only non-IID experiments in DFL literature, we conduct extensive experiments on multiple data non-IID scenarios, topology variations, model heterogeneity, and uncertainty quantification, demonstrating the practical advantages of DFedDG2. Our results show that DFedDG2 not only achieves communication efficiency but also provides better generalization and improved reliability compared to state-of-the-art approaches.


  • Calibrated Uncertainty Estimation for Trustworthy Deep IoT Attack Detection

    by Biprodip Pal, Saiful Islam, Alan Wee-Chung Liew

    The rapid proliferation of Internet of Things (IoT) devices has exposed us to a growing threat landscape. Advancements in artificial intelligence (AI), particularly deep learning (DL) techniques, offer innovative solutions for trustworthy IoT attack detection. Despite the resource-constrained nature of IoT devices, most existing AI-based IoT attack detection methods rely on complex deep learning models for automated feature extraction and generalization. However, DL models are inherently overconfident and tend to produce unreliable predictions both in-distribution and under distribution shifts when deployed. The large model size, coupled with deterministic and overconfident predictions, and limited focus on estimating the uncertainty, hinders the trustworthy deployment of DL models in applications where reliability is critical, not just high accuracy. In this paper, we present a framework for confidence calibration and uncertainty estimation of DL models in the context of IoT attack detection. Specifically, we propose a novel framework for the trustworthy design of deep IoT attack detection models, along with a lightweight DL model that achieves state-of-the-art (SoTA) attack detection performance. We demonstrate how both our DL model and other SoTA DL models can be effectively integrated into the proposed framework to ensure trustworthy IoT attack detection. Evaluated on the large-scale benchmark IoT-23 network traffic dataset in terms of calibration, uncertainty, and distribution shift, our approach delivers superior and trustworthy IoT attack detection performance.


  • CARBO: Clustering and rotation based oversampling for class imbalance learning

    by Mahit Kumar Paul, Biprodip Pal, A.H.M. Sarowar Sattar, A.S.M. Mustakim Rahman Siddique, Al Mehedi Hasan


  • Open Access

    Vulnerability in Deep Transfer Learning Models to Adversarial Fast Gradient Sign Attack for COVID-19 Prediction from Chest Radiography Images

    by Biprodip Pal, Debashis Gupta, Rashed- Al- Mahfuz, Salem A. Alyami, Mohammad Ali Moni

    The COVID-19 pandemic requires the rapid isolation of infected patients. Thus, high-sensitivity radiology images could be a key technique to diagnose patients besides the polymerase chain reaction approach. Deep learning algorithms are proposed in several studies to detect COVID-19 symptoms due to the success in chest radiography image classification, cost efficiency, lack of expert radiologists, and the need for faster processing in the pandemic area. Most of the promising algorithms proposed in different studies are based on pre-trained deep learning models. Such open-source models and lack of variation in the radiology image-capturing environment make the diagnosis system vulnerable to adversarial attacks such as fast gradient sign method (FGSM) attack. This study therefore explored the potential vulnerability of pre-trained convolutional neural network algorithms to the FGSM attack in terms of two frequently used models, VGG16 and Inception-v3. Firstly, we developed two transfer learning models for X-ray and CT image-based COVID-19 classification and analyzed the performance extensively in terms of accuracy, precision, recall, and AUC. Secondly, our study illustrates that misclassification can occur with a very minor perturbation magnitude, such as 0.009 and 0.003 for the FGSM attack in these models for X-ray and CT images, respectively, without any effect on the visual perceptibility of the perturbation. In addition, we demonstrated that successful FGSM attack can decrease the classification performance to 16.67% and 55.56% for X-ray images, as well as 36% and 40% in the case of CT images for VGG16 and Inception-v3, respectively, without any human-recognizable perturbation effects in the adversarial images. Finally, we analyzed that correct class probability of any test image which is supposed to be 1, can drop for both considered models and with increased perturbation; it can drop to 0.24 and 0.17 for the VGG16 model in cases of X-ray and CT images, respectively. Thus, despite the need for data sharing and automated diagnosis, practical deployment of such program requires more robustness.


  • A Deep Convolutional Neural Network Approach to Rice Grain Purity Analysis

    by Mushahidul Islam Shamim, Biprodip Pal, Anhad Singh Arora, Mahbubul Amin Pial


  • A Gaussian mixture based boosted classification scheme for imbalanced and oversampled data

    by Biprodip Pal, Mahit Kumar Paul

    Dataset with imbalanced class distribution used to abate classification performance for most of the standard classifier learning algorithms. Moreover, some application area consists of scarcity of labeled training data where clustering is most prominent way to support classification process. Gaussian Mixture Model (GMM) being able to approximate arbitrary probability distribution, is a dominant tool for classification in such cases by means of clustering. An ensemble approach is presented in this paper considering GMM as a weak learner to boost the GMMs in a semi supervised manner via Adaptive Boosting technique. This paper, firstly investigates how much K-means and GMM suffers from uneven class distribution in data. Later experiment on benchmark imbalanced datasets with different imbalance ratio and over sampled datasets using Synthetic Minority Over-sampling Technique (SMOTE) has been carried out for proposed approach. For each case cluster forest has been used as an attribute selection technique. Efficacy of the proposed Boosted GMM approach compared to standard clustering approaches like K means and GMM is exhibited from empirical analysis.


  • Gaussian mixture based semi supervised boosting for imbalanced data classification

    by Mahit Kumar Paul, Biprodip Pal

    Semi supervised approaches are practical in problem domain where pattern clustering is supposed to provide good classification. Gaussian Mixture Model (GMM) can approximate arbitrary probability distribution, thus is considered as a dominant tool for classification in such domains. This paper appraises the functioning for GMM as it is applied to imbalanced datasets which consists of uneven distribution of samples from all the classes. Later, an ensemble approach is presented to boost the GMMs in a semi supervised manner via Adaptive Boosting technique. Experiment on benchmark imbalanced datasets with different imbalance ratio has been carried out. Empirical result demonstrates the efficacy of the proposed Boosted GMM classifier compared to baseline approaches like K-means and GMM.