Welcome to the Security and Artificial Intelligence Lab
Our research group is situated within VinUniversity’s College of Engineering and Computer Science. We specialize in the field of trustworthy AI, with a core focus on simplifying the development and deployment of machine learning models while ensuring their robustness. Our research encompasses low-complexity generative approaches, strengthening algorithmic robustness, and tackling critical challenges in machine learning and federated learning to enhance security, privacy, efficiency, and fairness.
We are looking for passionate new PhD students, Postdocs, and Master students to join the team (more info) !
News
August, 2025
Our paper titled SC-GIR: Goal-oriented Semantic Communication via Invariant Representation Learning for Image Transmission has been accepted at IEEE Transactions on Mobile Computing (TMC).
August, 2025
HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation, pFedDSH: Enabling Knowledge Transfer in Personalized Federated Learning through Data-free Sub-Hypernetwork, and FLAT: Latent-Driven Arbitrary-Target Backdoor Attacks in Federated Learning released on arXiv.
July, 2025
BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning released on arXiv.
May, 2025
Two of our papers — FedDDF: Dynamic Dataset Filtering in Federated Large Language Model Training and FedKoE: Enhancing Federated Multimodal Learning through Knowledge of Experts — have been accepted at The International Workshop on Secure and Efficient Federated Learning in conjunction with ACM AsiaCCS 2025 (FL-AsiaCCS’25).
January, 2025
Our paper titled Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks has been accepted at The International Conference on Learning Representations (ICLR 2025). You can access the paper here.