To solve the privacy leakage problem faced by Internet of Vehicles (IoV) users when enjoying location-based services (LBS), a privacy-protecting predictive cache method based on blockchain and machine learning (BML-PPPCM) is proposed. First, a Bi-directional Long-Short Term Memory (Bi-LSTM) model is used to predict query requests over a future period based on historical request information. The predicted results are recommended to neighbors and broadcast to requestors. Then, deep Q-learning (DQN) is utilized to determine the optimal cache decision. Finally, a trust mechanism is introduced to calculate trust values, and blockchain is used to store transaction data and trust data, preventing malicious tampering by attackers. The simulation results show that BML-PPPCM has a higher cache hit ratio than other similar schemes and performs well in privacy protection and suppression of malicious and incentive denial of service providers.

中文翻译：

---

车联网中基于区块链和机器学习的隐私保护预测缓存方法


针对车联网（IoV）用户在享受位置服务（LBS）时面临的隐私泄露问题，提出一种基于区块链和机器学习的隐私保护预测缓存方法（BML-PPPCM）。首先，使用双向长短期记忆（Bi-LSTM）模型根据历史请求信息预测未来一段时间内的查询请求。预测结果会推荐给邻居并向请求者广播。然后，利用深度 Q 学习 (DQN) 来确定最佳缓存决策。最后引入信任机制计算信任值，并利用区块链存储交易数据和信任数据，防止攻击者恶意篡改。仿真结果表明，BML-PPPCM比其他同类方案具有更高的缓存命中率，并且在隐私保护和抑制服务提供商的恶意和激励拒绝方面表现良好。