Portrait of Dr. Sajib Mistry

Dr. Sajib Mistry

Collaborator, AI/ML Wing

Website

Affiliations

Ph.D Candidate
Curtin University, Australia

Publications (3)

Md Akil Raihan Iftee, Syed Md Ahnaf Hasan, Amin Ahsan Ali, AKM Mahbubur Rahman, Sajib Mistry, Aneesh Krishna

FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization

arXiv (Cornell University), pp. 3330-3339, 2025

Preprint / Working PaperDOI

data poisoning
Federated learning
surrogate models
feature consistency
Threat model
adversarial queries

Md Akil Raihan Iftee, Syed Md Ahnaf Hasan, Mir Sazzat Hossain, Rakibul Hasan Rajib, Amin Ahsan Ali, AKM Mahbubur Rahman, Sajib Mistry, Monowar Bhuyan

pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data

arXiv (Cornell University), 2025

Preprint / Working PaperDOI

test-time adaptation
domain shift
class imbalance
Federated learning
privacy-preserving federated learning
minority class performance

Rakibul Hasan Rajib, Md Akil Raihan Iftee, Mir Sazzat Hossain, A. K. M. Mahbubur Rahman, Sajib Mistry, M Ashraful Amin, Amin Ahsan Ali

FedCTTA: A Collaborative Approach to Continual Test-Time Adaptation in Federated Learning

2025 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2025

Conference PaperDOI URL

Federated learning
spatial heterogeneity
continual test-time adaptation
entropy minimization
privacy preservation
distribution shift
temporal heterogeneity

Projects (4)

How Good Must a Detector Be? Graded Semantic-Error Detection in Multi-Agent LLM Systems
pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data
FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization
FedRAPP: Federated Test-Time Prompt Tuning for Vision-Language Models with Reliability-Aware Prompt Personalization