Trustworthy, distributed, and efficient AI research
College of Engineering and Computer Science, VinUniversity
Robust, private, distributed, and efficient machine learning systems.
SAIL is the Security and Artificial Intelligence Lab at VinUniversity. We study and build machine learning systems that are trustworthy, distributed across real-world settings, and efficient enough for practical deployment.
The lab connects trustworthy AI, federated and distributed learning, privacy, robustness, backdoor attacks and defenses, edge AI, communication efficiency, and resource-aware machine learning.
We study how machine learning systems behave under uncertainty, distribution shifts, adversarial conditions, and privacy constraints. Our work focuses on robustness, privacy protection, backdoor attacks and defenses, trustworthy evaluation, and safer deployment.
Read moreWe design learning systems that work across distributed clients, data silos, institutions, and edge devices without centralizing private data. Our work includes federated learning, personalized learning, federated unlearning, fairness, communication efficiency, and cross-silo collaboration.
Read moreWe build efficient AI systems that reduce computation, communication, memory, and deployment cost. Our work studies resource-constrained learning, edge AI, efficient training, lightweight architectures, low-rank methods, and green AI infrastructure.
Read moreDistributed Learning / Trustworthy AI, 2026–2028. A research project on trustworthy federated learning for large language models, focusing on robustness, privacy, evaluation, and scalable collaboration.
Trustworthy AI / Distributed Learning. Federated learning methods for healthcare systems where privacy, robustness, and interpretability are central requirements.
Efficient Machine Learning. Resource-efficient AI training infrastructure with an emphasis on greener, scalable serverless computing.