The widespread integration of the Internet of Things (IoT) is crucial in advancing sustainable development. IoT service providers actively collect user data for analysis using sophisticated Deep Learning (DL) algorithms. This enables the extraction of valuable insights for business intelligence and improving service quality. However, as these datasets contain sensitive personal information, there is a risk of privacy breaches when DL models are employed. This vulnerability may result in Membership Inference Attacks (MIA), potentially leading to the unauthorized disclosure of highly sensitive data. Therefore, developing an efficient and privacy-preserving data analysis system for IoT is imperative. Recent research has highlighted the effectiveness of utilizing Bloom Filter (BF)-encoding in conjunction with Differential Privacy (DP) for safeguarding privacy during data analysis. Given its attributes of low complexity and high utility, this approach proves effective, particularly in resource-constrained IoT domains. With this in mind, we propose a novel framework for privacy-preserving IoT data analysis based on BF-encoded data. Our research introduces an innovative BF-encoding technique combined with Local Differential Privacy (LDP), capable of efficiently encoding various types of IoT data (such as facial images and smart-meter data) while maintaining privacy when integrated into DL algorithms for downstream analysis. Experimental results demonstrate that our BF-encoded data surpasses the utility of standard BF-encoded data when utilized in DL algorithms for downstream tasks, showcasing an approximate 30% improvement in classification accuracy. Furthermore, we assess the privacy of these DL models against MIA, revealing that attackers can only make random guesses with an accuracy of approximately 50%.

中文翻译：

---

用于物联网数据分析的隐私保护概率数据编码


物联网（IoT）的广泛融合对于推动可持续发展至关重要。物联网服务提供商使用复杂的深度学习 (DL) 算法积极收集用户数据进行分析。这使得能够提取有价值的商业智能见解并提高服务质量。然而，由于这些数据集包含敏感的个人信息，因此在使用深度学习模型时存在隐私泄露的风险。此漏洞可能会导致成员推断攻击 (MIA)，从而可能导致高度敏感数据未经授权的泄露。因此，开发一个高效且保护隐私的物联网数据分析系统势在必行。最近的研究强调了将布隆过滤器 (BF) 编码与差分隐私 (DP) 结合使用在数据分析过程中保护隐私的有效性。鉴于其低复杂性和高实用性的属性，这种方法被证明是有效的，特别是在资源有限的物联网领域。考虑到这一点，我们提出了一种基于 BF 编码数据的隐私保护物联网数据分析的新颖框架。我们的研究引入了一种与本地差分隐私 (LDP) 相结合的创新 BF 编码技术，能够有效地编码各种类型的物联网数据（例如面部图像和智能电表数据），同时在集成到深度学习算法中进行下游分析时保持隐私。实验结果表明，当用于下游任务的 DL 算法中时，我们的 BF 编码数据超越了标准 BF 编码数据的实用性，分类精度提高了约 30%。 此外，我们针对 MIA 评估了这些 DL 模型的隐私性，结果表明攻击者只能进行随机猜测，准确度约为 50%。