isl-logo


We are the Intelligent System (IntelliSys) Lab in the Computer Science Engineering Division. Our research bridges artificial intelligence (AI) and novel system architectures by designing efficient and robust AI algorithms and developing intelligent and high-performance computing systems. Check our roadmap.


News

05/24/2024 :calendar: Our TigerAI: LSU/IBM AI security summer boot camp has successfully completed. Check our exciting and fun moments!
05/19/2024 :airplane: Dr. Wang will give a talk about Critical Learning Periods in Federated Learning at the Smoky Mountain Workshop on Early Developmental Intelligence and Embodied Intelligence (EI2) (May 30–June 1).
05/17/2024 :pencil: Our paper “FedRoLA: Robust Federated Learning Against Model Poisoning via Layer-based Aggregation” has been accepted by KDD 2024—our another work on fine-grained FL attack & defense.
05/06/2024 :airplane: Dr. Wang visited Technical University of Munich (TUM) and gave a talk about personalized Federated Learning (pFL).
04/16/2024 :trophy: Our project “Harvesting Idle Resources Safely and Timely for Large-scale AI Applications in High-Performance Computing Systems” have been funded by the NSF OAC Core grant. Thanks NSF!
More...

Selected Publications

  1. HPDC
    Libra: Harvesting Idle Resources Safely and Timely in Serverless Clusters
    In Proceedings of the International Symposium on High-Performance Parallel and Distributed Computing (HPDC) 2023
  2. KDD
    CriticalFL: A Critical Learning Periods Augmented Client Selection Framework for Efficient Federated Learning
    In Proceedings of the ACM Special Interest Group on Knowledge Discovery and Data Mining (KDD) 2023
  3. ASPLOS
    RainbowCake: Mitigating Cold-starts in Serverless with Layer-wise Container Caching and Sharing
    In Proceedings of the ACM Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2024
  4. ICLR
    Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
    Accepted by the International Conference on Learning Representations (ICLR) 2024

Sponsors