arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.03151stat.MLcs.CRcs.CVcs.ITcs.LGmath.IT
收藏

深度私有特征提取

Deep Private-Feature Extraction

Sharif University of Technology(谢里夫理工大学);Queen Mary University of London(伦敦玛丽女王大学);Imperial College London(伦敦帝国理工学院)

Seyed Ali Osia, Ali Taheri, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Hamid R. Rabiee

摘要:

我们提出并评估了深度私有特征提取器(DPFE),这是一种基于信息论约束进行训练和评估的深度模型。通过在用户设备和服务提供商之间选择性地交换信息,DPFE使用户能够防止某些敏感信息与服务提供商共享,同时允许他们使用自己的模型提取经批准的信息。我们引入并利用对数秩隐私,一种新的措施来评估DPFE在删除敏感信息的有效性,并比较不同的模型的基础上,他们的准确性和隐私的权衡。然后,我们在智能手机上实现和评估DPFE的性能,以了解其复杂性,资源需求和效率权衡。我们在基准图像数据集上的结果表明,在适度的资源利用率下,DPFE可以实现高精度的主要任务,同时保护敏感特征的隐私。

英文摘要:

We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service provider, DPFE enables the user to prevent certain sensitive information from being shared with a service provider, while allowing them to extract approved information using their model. We introduce and utilize the log-rank privacy, a novel measure to assess the effectiveness of DPFE in removing sensitive information and compare different models based on their accuracy-privacy tradeoff. We then implement and evaluate the performance of DPFE on smartphones to understand its complexity, resource demands, and efficiency tradeoffs. Our results on benchmark image datasets demonstrate that under moderate resource utilization, DPFE can achieve high accuracy for primary tasks while preserving the privacy of sensitive features.

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。

↑