collaborators

10 papers

cs.LG2026

Analysis of Federated Aggregation under Model Poisoning and Backdoor Attacks: A Reconstructed Cross-Dataset and Cross-Architecture Benchmark

Soumya Mazumdar, Vineet Kumar Rakesh, Tapas Samanta

Robust comparisons of federated aggregation methods require joint consideration of predictive performance, threat definitions, metric semantics, and execution provenance. A 500-cel…

cs.CV2026

A HamNoSys-Guided Dataset and Baselines for Fine-Grained Isolated Handshape Recognition in Sign Language

Ushnish Sarkar, Suvajit Patra, Bhaswar Chattopadhyay +2

Purpose: Fine-grained handshape recognition supports computational sign-language transcription, recognition, and translation, but broad, phonetically defined visual inventories wit…

cs.LG2026

DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting

Rahil Aftab, Vineet Kumar Rakesh, Soumya Mazumdar +1

Federated learning repeatedly incurs local optimization and model-update transmission. We study DG-FedReuse, a simulator-level mechanism that allows selected clients to contribute…

cs.CR2026

RES-DARE: Failure-Aware Expert Adaptation and Rollback-Safe Self-Repair for Intrusion Detection

Rahil Aftab, Anyash Prasad, Soumya Mazumdar +2

Intrusion detection systems are often trained under static benchmark conditions, although deployed network environments are affected by traffic drift, sensor noise, changing worklo…

cs.CR2026

PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation

Soumya Mazumdar, Vineet Kumar Rakesh, Tapas Samanta

Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech datasets, raising major priva…

cs.CV2026

BayesFusion-SDF: Probabilistic Signed Distance Fusion with View Planning on CPU

Soumya Mazumdar, Vineet Kumar Rakesh, Tapas Samanta

Key part of robotics, augmented reality, and digital inspection is dense 3D reconstruction from depth observations. Traditional volumetric fusion techniques, including truncated si…