Projects

Research in motion.

Projects connect SAIL’s research pillars with concrete systems, benchmarks, and application areas.

Active projects

Current lines of work across trustworthy AI, distributed learning, and efficient machine learning.

active

TrustFed: Trustworthy Federated Large Language Models

A research project on trustworthy federated learning for large language models, focusing on robustness, privacy, evaluation, and scalable collaboration.

Funded by the Accelerating Research Excellence Program, VinUniversity. Principal Investigator: Prof. Kok-Seng Wong.

Timeline: 2026–2028

Federated learningLarge language modelsTrustworthy AIPrivacyRobustness
Related papers
  • FedDDF: Dynamic Dataset Filtering in Federated Large Language Model Training
active

Privacy-Preserving, Robust, and Explainable Federated Learning for Healthcare

Federated learning methods for healthcare systems where privacy, robustness, and interpretability are central requirements.

Healthcare AIPrivacyRobustnessExplainabilityCross-silo learning
Related papers
  • Personalized Privacy-Preserving Framework for Cross-Silo Federated Learning
  • On the Trade-off Between Privacy Protection and Data Utility for Chest X-ray Images
active

Green Serverless Computing for Resource-Efficient AI Training

Resource-efficient AI training infrastructure with an emphasis on greener, scalable serverless computing.

Green AIResource efficiencyServerless computingEfficient training
Related papers
  • Memory-efficient Continual Learning with Prototypical Exemplar Condensation
active

Robust Federated Learning under Backdoor Threats

Benchmarking, understanding, and improving the robustness of federated learning systems under adversarial conditions.

Federated learningRobustnessBackdoor attacks and defensesBenchmarking
Related papers
  • BackFed: A Standardized and Efficient Benchmark Framework for Evaluating Backdoor Attacks in Federated Learning
  • Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions
  • FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection
active

Efficient Federated Learning on Edge Devices

Federated learning methods for edge and IoT environments where memory, communication, and compute are constrained.

Edge AICommunication efficiencyResource-constrained learningClient heterogeneity
Related papers
  • An Empirical Study of Federated Learning on IoT-Edge Devices: Resource Allocation and Heterogeneity
  • FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Co-Training

Completed projects

Completed projects remain visible to show the lab’s research history.

completed

Privacy-Preserving Data Publishing for Autonomous Vehicles

Privacy-preserving data publishing methods for autonomous vehicle systems and mobility data.

Timeline: 2021–2023

PrivacyAutonomous systemsData publishingTrust
Related papers
  • Emerging Privacy and Trust Issues for Autonomous Vehicle Systems