一种有效的局部差分隐私的隐私-效用保护推荐系统
A Validated Privacy-Utility Preserving Recommendation System with Local Differential Privacy
摘要：
本文提出了一种新的推荐系统保护隐私和效用。它依赖于本地的差分隐私（LDP）的浏览用户发送他的嘈杂的偏好配置文件，扰动布隆过滤器，服务提供商。这种方法的独创性是多方面的。首先，据我们所知，该方法是第一个在用户侧包括两个扰动轮- PRR（永久随机响应）和IRR（瞬时随机响应）-在一个完整的用户简档。其次，建立了完整的验证实验链，使用基于神经网络或XGBoost的机器学习解码算法对扰动后的Bloom过滤器进行解码，使用聚类Kmeans工具对用户进行聚类。第三，大量的实验表明，我们的方法实现了良好的实用性和隐私的权衡，即90 $\%$聚类成功率，分别。80.3 $\%$，分别用于LDP $ε= 0.8$的值。$ε= 2$。第四，实验和理论分析给出了具体的结果，我们的方法的阻力合理的可否认性和抵抗平均攻击。
英文摘要：
This paper proposes a new recommendation system preserving both privacy and utility. It relies on the local differential privacy (LDP) for the browsing user to transmit his noisy preference profile, as perturbed Bloom filters, to the service provider. The originality of the approach is multifold. First, as far as we know, the approach is the first one including at the user side two perturbation rounds - PRR (Permanent Randomized Response) and IRR (Instantaneous Randomized Response) - over a complete user profile. Second, a full validation experimentation chain is set up, with a machine learning decoding algorithm based on neural network or XGBoost for decoding the perturbed Bloom filters and the clustering Kmeans tool for clustering users. Third, extensive experiments show that our method achieves good utility-privacy trade-off, i.e. a 90$\%$ clustering success rate, resp. 80.3$\%$ for a value of LDP $ε= 0.8$, resp. $ε= 2$. Fourth, an experimental and theoretical analysis gives concrete results on the resistance of our approach to the plausible deniability and resistance against averaging attacks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
