一种社交网络中细粒度人脸隐私保护方案

A Fine-Grained Face Privacy Protection Scheme in Social Networks

庞大的用户规模、海量的信息交互、多元化的系统服务导致社交网络中存在巨量的以图像形式为主的共享数据。而由于现有人脸图像敏感信息的访问控制粒度较粗,使得共享数据在社交网络中广泛传播的同时,人脸敏感信息泄露问题严重,甚至引发恶性事件。文章通过构造发布者和访问者与访问资源之间的细粒度社交关系,将访问控制单元细化到人脸图像块,结合AES加密、属性基加密和分布式人脸识别,提出了一种对图像中人脸敏感信息进行细粒度隐私保护的方案。该方案实现了图片分享的过程中,人脸敏感信息只能被特定访问者获取的细粒度、动态访问控制策略,保证了图片数据在分享和访问过程中的隐私信息的安全性。

In social networks, the large scale of users, the interaction of mass information and the diversity of services lead to a large amount of shared data, which mainlyformed by images. The coarse-grained access control scheme for sensitive facial information of images makes the shared data spread widely in existing social networks and also causes severe problems in revealing facial sensitive information, and even leads to vicious incidents. By establishing fine-grained relationships among publishers, visitors and accessing resources, subdividing access control cell into facial patches. Proposed a scheme for fine-grained protection offacial sensitive information of images, combining the AES encryption with the attribute-based encryption and the mixing distributed face recognition.A finegrained facial sensitive information protection scheme is proposed. The scheme realizes the fine-grain and dynamic access control strategy which can ensure the sensitive facial information only be revealed to special visitors while images sharing, achieves the security of facial sensitive information while sharing and accessing.