Browsing by Author "Cao, Yuanlong"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Blockchain and distributed digital watermarking effort on federated learning: innovating intellectual property protection
    (IEEE, 2024-12-02) Chao, Kailin; Li, JunJie; Jiang, Yirui; Xiao, Jianmao; Cao, Yuanlong
    Federated Learning with Digital Watermarks (FLDW) have been recognized as a promising solution for property protection. However, the existing FLDW-related technologies neglect the requirements of decentralized settings, leading to recurrent issues such as discrepancies in distributed client data. This paper introduces a Blockchain Federated Learning Intellectual Property Protection Framework (BFLIPR), to address the data security and model validation challenges in decentralized federated learning environments. BFLIPR merges blockchain, digital watermarking, and federated learning technologies. By harnessing the blockchain’s tamper-proof properties, digital watermarking’s concealment capabilities, and federated learning’s distributed feature, the framework offers a solution that aligns with intellectual property protection mechanism, to bolster data security and property safeguarding. Experimental findings demonstrate its high feasibility and robust for data privacy and model security in the federated learning.
  • Thumbnail Image
    ItemOpen Access
    ROSE+ : A robustness-optimized security scheme against cascading failures in multipath TCP under LDDoS attack streams
    (IEEE, 2024-12-17) Nie, Jinquan; Ji, Lejun; Jiang, Yirui; Ma, Young; Cao, Yuanlong
    Multipath TCP leverages parallel data transmission across multiple paths to improve transmission rates, reliability, and resource utilization. However, Multipath TCP faces severe network security and communication reliability challenges when exposed to low-rate distributed denial-of-service (LDDoS) attacks. In this paper, we propose a robustness optimization security scheme against cascading failures in Multipath TCP (ROSE+) to tackle the challenges posed by Low-rate Distributed Denial of Service (LDDoS) attacks on network security and communication reliability. The scheme integrates the intricate network load-capacity cascading failures model and leverages the unique characteristics of multipath TCP to facilitate the redistribution of load traffic at ineffectiveness nodes, thereby alleviating the cascading failures induced by LDDoS attack streams. Additionally, we optimize the robustness of communication transmission systems by devising a load-capacity cascading failures model. The experimental results demonstrate that the scheme reduces the probability of cascading failures by 20.07%. This research provides new ideas and methods to improve the robustness and destruction resistance of multipath TCP transmission.