TLTao Liu

Tao Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tao Liu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Budgeted Coreset Learning for Deadline-Constrained Federated Learning in Industrial IoT

    by Xiuheng Liao, Zhaoyang Han, Tao Liu, Zhiwei Si, Weiyu Wang, Di Wu, Chunhua Su

  • Top Cited Papers

    Fully Decentralized Authentication and Key Exchange Scheme for Data Sharing in AIoMT

    by Yangfan Liang, Jingxue Chen, Lina Bu, Tao Liu, Xiaopei Wang, Bin Wang, Guodao Zhang, Hong Sun

    The convergence of edge intelligence and networked medical infrastructures in the Artificial Intelligence of Medical Things (AIoMT) is transforming healthcare toward personalization and predictive intervention. In this paradigm, high-resolution physiological data continuously flow between wearable or implantable devices, edge nodes, and cloud analytics platforms. Such connectivity enables advanced diagnostic modeling and real-time decision support. However, it also enlarges the attack surface. AIoMT components are exposed to impersonation, replay, and man-in-the-middle attacks. Therefore, secure data exchange becomes essential. Authentication and key exchange (AKE) schemes address this requirement by enabling mutual authentication and session key establishment over insecure channels. Nevertheless, many existing centralized designs suffer from single points of failure and insider threats. Several blockchain-assisted approaches still retain centralized identity traceability. In addition, most AKE schemes either neglect physical security, lack tolerance to intrinsic physical unclonable function (PUF) noise, or store sensitive PUF challenge–response pairs, which increases the risk of modeling attacks. To address these issues, we propose a fully decentralized authentication and key exchange scheme (FDAKES) for AIoMT. FDAKES adopts a $(t,n)$ threshold-based root of trust across multiple registration centers (MRCs) to remove unilateral control in registration and tracing. Its server-independent AKE process combines threshold-protected identities, dynamic nonces, timestamps, and PUF and biometric enhanced credentials to achieve perfect forward secrecy. Decentralized conditional traceability preserves user anonymity while allowing identity recovery only with unanimous MRCs consent. By integrating PUF with a fuzzy extractor, FDAKES enables stable secret regeneration without storing raw challenge–response pairs, thereby mitigating modeling threats. We formally prove protocol correctness for login authentication and mutual key agreement. We further establish semantic security of the session key under the real-or-random model, showing that the adversary advantage is negligible in the random oracle model. An extensive informal analysis demonstrates resistance to impersonation, replay, guessing, modeling, physical, man-in-the-middle, and key compromise attacks. Experimental evaluation demonstrates that FDAKES reduces total computational overhead by up to 40.95% and at least 17.25% percent compared with recent state-of-the-art AKE schemes, while communication cost is reduced by up to 76.73% and at least 5% across representative baselines. This work establishes a robust and fully decentralized trust foundation for next-generation smart healthcare systems.


  • Efficient Edge Deployment of Mixture-of-Experts Models with Hybrid Expert Quantization

    by Tao Liu, Qipeng Xie, Zhaoyang Han, Weizheng Wang, Shengli Pan, Xiang Zhang, Chunhua Su, Kaishun Wu

    Deploying large language models (LLMs) directly at the edge offers significant benefits in reducing inference latency and enhancing privacy protection. However, this approach presents critical technical challenges due to the limited hardware resources available at the edge. In this paper, we explore the deployment of the Mixture-of-Experts (MoE) model, a popular LLM architecture, using weight quantization in a typical edge environment with multiple edge servers. Existing methods that uniformly quantize MoE models do not account for the varying importance of different experts or the dynamic nature of edge requests. To address these issues, we propose a hybrid expert quantization strategy, where each edge server quantizes experts to different bit-widths based on the preferences of received requests. Furthermore, we implement a comprehensive system optimization that jointly considers expert quantization and request assignment, aiming to achieve high-precision and low-latency inference services. To manage the complex, coupled optimization challenges, we design a reinforcement learning (RL)-based algorithm. To overcome the slow convergence typical of traditional RL, we pre-train the policy network using a system simulator that generates heuristic solutions, thus accelerating the learning process. Extensive experimental results on real datasets demonstrate that our approach significantly outperforms existing methods.


  • Streaming Graph Learning in IoT With Storage Optimization and Communication Reduction

    by Tao Liu, Shengli Pan, Peng Li

    Graph neural networks (GNNs) have shown great success in IoT applications, but many IoT scenarios further involve evolving graph data over time. Streaming graph learning (SGL) tackles the issue by updating GNN models continuously, incorporating significant historical node data for tasks like node classification. However, existing research on SGL often neglects memory limitations during historical node selection, and efficient distributed training is challenging due to the coupling of node selection, placement, and parallelization. This article proposes an efficient distributed SGL system that optimizes node selection and storage in multi-GPU environments, while reducing communication overhead to accelerate training. Extensive evaluations demonstrate the effectiveness of the approach.


  • Efficient Inference of Graph Neural Networks Using Local Sensitive Hash

    by Tao Liu, Peng Li, Zhou Su, Mianxiong Dong

    Graph neural networks (GNNs) have attracted significant research attention because of their impressive capability in dealing with graph-structure data, such as energy networks, that are crucial for sustainable computing. We find that the communication of data loading from main memory to GPUs is the main bottleneck of GNN inference because of redundant data loading. In this paper, we propose RAIN, an efficient GNN inference system for graph learning. There are two key designs. First, we explore the opportunity of conducting similar inference batches sequentially and reusing repeated nodes among adjacent batches to reduce redundant data loading. This method requires reordering the batches based on their similarity. However, comparing the similarity across a large number of inference batches is a difficult task with a high computational cost. Thus, we propose a local sensitive hash (LSH)-based clustering scheme to group similar batches together quickly without pair-wise comparison. Second, RAIN contains an efficient adaptive sampling strategy, allowing users to sample target nodes' neighbors according to their degree. The number of sampled neighbors is proportional to the size of the node's degree. We conduct extensive experiments with various baselines. RAIN can achieve up to 6.8X acceleration, and the accuracy decrease is smaller than 0.1%.


  • S-Glint: Secure Federated Graph Learning With Traffic Throttling and Flow Scheduling

    by Tao Liu, Peng Li, Yu Gu, Zhou Su

    Federated learning has been proposed as a promising distributed machine learning paradigm with strong privacy protection on training data. In this paper, we study federated graph learning (FGL) under a cross-silo setting where several servers are connected by a wide-area network and cooperate in training a graph convolutional network (GCN) model. We find that communication becomes the main system bottleneck because of frequent information exchanges among federated severs and limited network bandwidth. To tackle this challenge, we design S-Glint, a secure federated graph learning system, containing a homomorphic encryption-based protocol with pre-aggregation and batching strategies. The network traffic throttling and flows scheduling are also proposed to accelerate the learning process. To evaluate the effectiveness of S-Glint, we conduct experiments using trace-driven simulations. The results show that S-Glint can significantly outperform existing federated learning solutions.