activity
20242026
collaborators

5 papers

stat.ML2026

DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing

Utsab Saha, Tanvir Muntakim Tonoy, Hafiz Imtiaz

In recent years, the growth of data across various sectors, including healthcare, security, finance, and education, has created significant opportunities for analysis and informed…

cs.CV2025

CAE-Net: Generalized Deepfake Image Detection using Convolution and Attention Mechanisms with Spatial and Frequency Domain Features

Anindya Bhattacharjee, Kaidul Islam, Kafi Anan +4

The spread of deepfakes poses significant security concerns, demanding reliable detection methods. However, diverse generation techniques and class imbalance in datasets create cha…

stat.ML2025

Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise

Utsab Saha, Tanvir Muntakim Tonoy, Hafiz Imtiaz

In this work, we explore differentially private synthetic data generation in a decentralized-data setting by building on the recently proposed Differentially Private Class-Centric…

cs.LG2025

Load Forecasting on A Highly Sparse Electrical Load Dataset Using Gaussian Interpolation

Chinmoy Biswas, Nafis Faisal, Vivek Chowdhury +5

Sparsity, defined as the presence of missing or zero values in a dataset, often poses a major challenge while operating on real-life datasets. Sparsity in features or target data o…

eess.IV2024

Contextual Checkerboard Denoise -- A Novel Neural Network-Based Approach for Classification-Aware OCT Image Denoising

Md. Touhidul Islam, Md. Abtahi M. Chowdhury, Sumaiya Salekin +3

In contrast to non-medical image denoising, where enhancing image clarity is the primary goal, medical image denoising warrants preservation of crucial features without introductio…