JLJunxu Liu

Junxu 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

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Junxu Liu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PrivFDM: Differentially Private Federated Diffusion Models for Image Synthesis

    by Wenbo Yu, Qingqing Ye, Sen Zhang, Junxu Liu, Haibo Hu

    Deploying Diffusion Models (DMs) in federated settings has recently attracted growing attention for their ability to harness the strong generative capacity of diffusion models. However, their practical deployment remains hindered by privacy risks, as sharing local models can potentially leak sensitive training data. To mitigate this, we propose PrivFDM, a differentially private federated diffusion model for image synthesis that generates high-fidelity synthetic images while ensuring rigorous privacy guarantees. PrivFDM presents a local pre-training method with autoencoder?based data perturbation that injects DP noise directly into the low?dimensional representations of the training data. This design reduces data sensitivity and significantly lowers privacy budget consumption. To support effective and private learning under heterogeneous client data, we further develop a local fine-tuning strategy with model perturbation and common knowledge sharing. By integrating DP?SGD and conditioning diffusion models through label embeddings, our approach mitigates the disruptive effect of client divergence and enhances the utility of the synthesized images. We theoretically prove that PrivFDM ensures DP guarantees across the entire federated training pipeline. Extensive experiments on multiple datasets demonstrate the strong performance and practical advantages of the proposed PrivFDM in federated learning.

  • Open Access

    Cross-silo Federated Learning with Record-level Personalized Differential Privacy

    by Junxu Liu, Jian Lou, Li Xiong, Jinfei Liu, Xiaofeng Meng

    Federated learning (FL) enhanced by differential privacy has emerged as a popular approach to better safeguard the privacy of client-side data by protecting clients' contributions during the training process. Existing solutions typically assume a uniform privacy budget for all records and provide one-size-fits-all solutions that may not be adequate to meet each record's privacy requirement. In this paper, we explore the uncharted territory of cross-silo FL with record-level personalized differential privacy. We devise a novel framework namedrPDP-FL, employing a two-stage hybrid sampling scheme with both uniform client-level sampling and non-uniform record-level sampling to accommodate varying privacy requirements. A critical and non-trivial problem is how to determine the ideal per-record sampling probability q given the personalized privacy budget ε. We introduce a versatile solution namedSimulation-CurveFitting, allowing us to uncover a significant insight into the nonlinear correlation between q and ε and derive an elegant mathematical model to tackle the problem. Our evaluation demonstrates that our solution can provide significant performance gains over the baselines that do not consider personalized privacy preservation.


  • Open Access

    Personalized Differentially Private Federated Learning without Exposing Privacy Budgets

    by Junxu Liu, Jian Lou, Li Xiong, Xiaofeng Meng

    The meteoric rise of cross-silo Federated Learning (FL) is due to its ability to mitigate data breaches during collaborative training. To further provide rigorous privacy protection with consideration of the varying privacy requirements across different clients, a privacy-enhanced line of work on personalized differentially private federated learning (PDP-FL) has been proposed. However, the existing solution for PDP-FL [20] assumes the raw privacy budgets of all clients should be collected by the server. These values are then directly utilized to improve the model utility via facilitating the privacy preferences partitioning (i.e., partitioning all clients into multiple privacy groups). It is however non-realistic because the raw privacy budgets can be quite informative and sensitive. In this work, our goal is to achieve PDP-FL without exposing clients' raw privacy budgets by indirectly partitioning the privacy preferences solely based on clients' noisy model updates. The crux lies in the fact that the noisy updates could be influenced by two entangled factors of DP noises and non-IID clients' data, leaving it unknown whether it is possible to uncover privacy preferences by disentangling the two affecting factors. To overcome the hurdle, we systematically investigate the unexplored question of under what conditions can the model updates of clients be primarily influenced by noise levels rather than data distribution. Then, we propose a simple yet effective strategy based on clustering the L2 norm of the noisy updates, which can be integrated into the vanilla PDP-FL to maintain the same performance. Experimental results demonstrate the effectiveness and feasibility of our privacy-budget-agnostic PDP-FL method.


  • Analysis and Assessment of Power System Source-Network-Load-Storage Intrinsic Safety Risk

    by Junxu Liu, Zhaojun Lu, Peiying Gan, Jun Wu, Jing Guo, Daipeng Jiang

    Since the development of source, network, load and storage, a series of risks have been brought to the power system, whose safe and stable operation is threatened. It is of great significance to study the intrinsic safety risk assessment of power system for risk management and control. First, according to the concept of intrinsic safety, the definition and connotation of the essential security of the power system were put forward, emphasizing that planning is the fundamental guarantee for improving the intrinsic safety level; Then, based on the probabilistic load flow and Monte Carlo simulation method, a power system risk assessment methods and processes that takes into account the uncertainty of new energy and load were proposed; Next, safety and economic risk indicators and weighting methods were proposed to establish system risk calculation methods; Finally, the case analysis was carried out based on IEEE-39 node system for risk assessment, and the impact of changes in source, load, and storage on risk was discussed in different scenarios.