Research
SAIL organizes its work around three connected pillars spanning AI security, privacy, federated systems, communication efficiency, and practical deployment.
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.
We 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.
We 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.
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.
Distributed Learning / Trustworthy AI. 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.
Trustworthy AI. Privacy-preserving data publishing methods for autonomous vehicle systems and mobility data.
Trustworthy AI / Distributed Learning. Benchmarking, understanding, and improving the robustness of federated learning systems under adversarial conditions.
We 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.
Distributed Learning / Trustworthy AI. 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.
Trustworthy AI / Distributed Learning. Benchmarking, understanding, and improving the robustness of federated learning systems under adversarial conditions.
Efficient Machine Learning / Distributed Learning. Federated learning methods for edge and IoT environments where memory, communication, and compute are constrained.
We 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.
Distributed Learning / Trustworthy AI. A research project on trustworthy federated learning for large language models, focusing on robustness, privacy, evaluation, and scalable collaboration.
Efficient Machine Learning. Resource-efficient AI training infrastructure with an emphasis on greener, scalable serverless computing.
Efficient Machine Learning / Distributed Learning. Federated learning methods for edge and IoT environments where memory, communication, and compute are constrained.