提出去中心化隐私保护入侵检测框架，防数据泄露与恶意攻击。
PenTiDef: Decentralized Federated Intrusion Detection System with Differential Privacy and Latent-Space Defense via Blockchain Coordination in IIoT
- 客户端差分隐私加噪+潜空间特征压缩，防梯度泄露与投毒。
- 在非独立同分布下，40%攻击者时仍保持92%以上检测准确率。
- 区块链协同聚合，适合工业物联网等高风险场景使用。
本文提出PenTiDef，一种完全去中心化的隐私保护中毒鲁棒联邦入侵检测框架（DFL-IDS）。该框架融合三项核心技术：(i) 客户端侧分布式差分隐私（DDP）结合随机高斯噪声，防范梯度泄露；(ii) 轻量级潜空间防御模块，通过自编码器提取并压缩倒数第二层表示（PLRs），生成稳定潜在语义表示（LSRs），再利用中心核对齐（CKA）与K均值聚类实现无需辅助数据的恶意更新检测；(iii) 可信区块链层搭载智能合约，实现链上验证、安全联邦平均聚合与不可篡改审计，彻底消除中心服务器。在CIC-IDS2018与Edge-IIoTSet数据集上，于独立同分布（IID）与真实非独立同分布（non-IID）设置下，最高支持40%攻击者比例，实验表明PenTiDef在检测准确率与F1分数上持续优于前沿基线（FLARE与FedCC），同时训练开销更低。通过统一协议联合解决隐私、鲁棒性与去中心化问题，为异构、对抗性强的工业物联网环境提供可信赖的协作入侵检测方案。
原文摘要 · Abstract (English)
This paper proposes PenTiDef, a fully decentralized, privacy-preserving, and poisoning-resilient framework for decentralized federated IDS (DFL-IDS). PenTiDef synergistically integrates three key components: (i) client-side Distributed Differential Privacy (DDP) with stochastic Gaussian noise to protect gradient leakage, (ii) a lightweight latent-space defense module that extracts and compresses penultimate-layer representations (PLRs) into stable Latent Semantic Representations (LSRs) via AutoEncoder, followed by Centered Kernel Alignment (CKA) and K-Means clustering for robust malicious update detection without auxiliary datasets, and (iii) a permissioned blockchain layer with smart contracts that orchestrates on-chain validation, secure FedAvg aggregation, and immutable auditability, eliminating any central server. Extensive experiments on CIC-IDS2018 and Edge-IIoTSet under both IID and realistic non-IID settings, with adversary ratios up to 40\%, demonstrate that PenTiDef consistently outperforms state-of-the-art baselines (FLARE and FedCC) in detection accuracy and F1-score while maintaining lower training overhead. By jointly addressing privacy, robustness, and decentralization in a unified secure aggregation protocol, PenTiDef provides a practical and scalable solution for trustworthy collaborative intrusion detection in heterogeneous, adversarial IIoT environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。