Publications
Lab published papers.
A curated publication list focused on trustworthy AI, federated learning, privacy, robustness, and efficient machine learning. We prioritize publishing in top-tier, peer-reviewed AI/ML venues. Our recent contributions have been accepted at leading conferences such as CVPR, NeurIPS, ECCV, ICML, ICLR, AAAI, ACL, WWW, and WACV.
2026
- MCP: From Context Compression to Mining for Efficient RAG-based LLM Serving IEEE ICDM 2026: A*
- GARFIELD: Graph-Adaptive SSM for Explainable 3D Multi-Person WiFi Pose Estimation BMVC 2026: A
- HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning preprint Preprint
- H-SFP: Hierarchical Federated Learning with Decoupled Split-Model Prototyping ECCV 2026: A*
- Rethinking Molecular Graph Backdoors under Chemistry-aware Admission preprint Preprint
- When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning preprint Preprint
- BackFed: A Standardized and Efficient Benchmark Framework for Evaluating Backdoor Attacks in Federated Learning ICLR 2026 Workshop Paper
- HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation CVPR 2026: A* PaperPreprint
- Memory-efficient Continual Learning with Prototypical Exemplar Condensation CVPR 2026 Findings: A* (CVPR) Preprint
- Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning CVPR 2026 Findings: A* (CVPR) PaperPreprint
- Clean-Label Physical Backdoor Attacks with Data Distillation AAAI 2026: A* PaperPreprint
- Interleaved Selective State Space Models for Efficient WiFi-Based 3D Multi-Person Pose Estimation ICML 2026: A* Paper
2025
- An Empirical Study of Federated Learning on IoT-Edge Devices: Resource Allocation and Heterogeneity IEEE Transactions on Neural Networks and Learning Systems 2025: Impact Factor 8.9 PaperPreprint
- SC-GIR: Goal-oriented Semantic Communication via Invariant Representation Learning for Image Transmission IEEE Transactions on Mobile Computing 2025: Impact Factor 9.2 PaperPreprint
- Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks ICLR 2025: A* PaperPaper
- FedDDF: Dynamic Dataset Filtering in Federated Large Language Model Training FL-AsiaCCS 2025 Workshop Paper
- FedKoE: Enhancing Federated Multimodal Learning through Knowledge of Experts FL-AsiaCCS 2025 Workshop Paper
- FLAT: Latent-Driven Arbitrary-Target Backdoor Attacks in Federated Learning preprint Preprint
2024
- Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions Engineering Applications of Artificial Intelligence 2024: Impact Factor 8.0 Paper
- Benchmarking Federated Few-Shot Learning for Video-Based Action Recognition IEEE Access 2024: Impact Factor 3.6 Paper
- Personalized Privacy-Preserving Framework for Cross-Silo Federated Learning IEEE Transactions on Emerging Topics in Computing 2024: Impact Factor 5.4 Paper
- Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization CVPR 2024: A* PaperPreprint
- Fooling the Textual Fooler via Randomizing Latent Representations Findings of ACL 2024: A* (ACL) PaperPreprint
- HPE-Li: WiFi-enabled Lightweight Dual Selective Kernel Convolution for Human Pose Estimation ECCV 2024: A* Paper
- Towards Efficient Communication Federated Recommendation System via Low-rank Training The Web Conference 2024: A* PaperPreprint
- Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks ICLR 2024: A* Preprint
- FedFSLAR: A Federated Learning Framework for Few-shot Action Recognition WACV 2024 Workshop Paper
- Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape preprint Preprint
- Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learning preprint Preprint
2023
- FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Co-Training IEEE Transactions on Network and Service Management 2023: Impact Factor 4.7 PaperPreprint
- An Empirical Study of Federated Unlearning: Efficiency and Effectiveness ACML 2023: Unranked Paper
- FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection IJCNN 2023: B PaperPreprint
- IBA: Towards Irreversible Backdoor Attacks in Federated Learning NeurIPS 2023: A* Paper
2022
- Toward Efficient Hierarchical Federated Learning Design Over Multi-Hop Wireless Communications Networks IEEE Access 2022: Impact Factor 3.9 Paper
- Emerging Privacy and Trust Issues for Autonomous Vehicle Systems ICOIN 2022: Unlisted Paper
- On the Trade-off Between Privacy Protection and Data Utility for Chest X-ray Images ATC 2022: Unlisted Paper
2021
- Efficient two-party integer comparison with block vectorization mechanism IEEE Access 2021: Impact Factor 3.476 Paper