Biblio

While cloud-based deep learning benefits for high-accuracy inference, it leads to potential privacy risks when exposing sensitive data to untrusted servers. In this paper, we work on exploring the feasibility of steganography in preserving inference privacy. Specifically, we devise GHOST and GHOST+, two private inference solutions employing steganography to make sensitive images invisible in the inference phase. Motivated by the fact that deep neural networks (DNNs) are inherently vulnerable to adversarial attacks, our main idea is turning this vulnerability into the weapon for data privacy, enabling the DNN to misclassify a stego image into the class of the sensitive image hidden in it. The main difference is that GHOST retrains the DNN into a poisoned network to learn the hidden features of sensitive images, but GHOST+ leverages a generative adversarial network (GAN) to produce adversarial perturbations without altering the DNN. For enhanced privacy and a better computation-communication trade-off, both solutions adopt the edge-cloud collaborative framework. Compared with the previous solutions, this is the first work that successfully integrates steganography and the nature of DNNs to achieve private inference while ensuring high accuracy. Extensive experiments validate that steganography has excellent ability in accuracy-aware privacy protection of deep learning.

Dynamic searchable symmetric encryption (DSSE) that enables a client to perform searches and updates on encrypted data has been intensively studied in cloud computing. Recently, forward privacy and backward privacy has engaged significant attention to protect DSSE from the leakage of updates. However, the research in this field almost focused on keyword-level updates. That is, the client needs to know the keywords of the documents in advance. In this paper, we proposed a document-level update scheme, DBP, which supports immediate deletion while guaranteeing forward privacy and backward privacy. Compared with existing forward and backward private DSSE schemes, our DBP scheme has the following merits: 1) Practicality. It achieves deletion based on document identifiers rather than document/keyword pairs; 2) Efficiency. It utilizes only lightweight primitives to realize backward privacy while supporting immediate deletion. Experimental evaluation on two real datasets demonstrates the practical efficiency of our scheme.

Cloud computing has become an important and popular infrastructure for data storage and sharing. Typically, data owners outsource their massive data to a public cloud that will provide search services to authorized data users. With privacy concerns, the valuable outsourced data cannot be exposed directly, and should be encrypted before outsourcing to the public cloud. In this paper, we focus on k-Nearest Neighbor (k-NN) search over encrypted data. We propose efficient and secure k-NN search schemes based on matrix similarity to achieve efficient and secure query services in public cloud. In our basic scheme, we construct the traces of two diagonal multiplication matrices to denote the Euclidean distance of two data points, and perform secure k-NN search by comparing traces of corresponding similar matrices. In our enhanced scheme, we strengthen the security property by decomposing matrices based on our basic scheme. Security analysis shows that our schemes protect the data privacy and query privacy under attacking with different levels of background knowledge. Experimental evaluations show that both schemes are efficient in terms of computation complexity as well as computational cost.

One critical challenge of today's cloud services is how to provide an effective search service while preserving user privacy. In this paper, we propose a wildcard-based multi-keyword fuzzy search (WMFS) scheme over the encrypted data, which tolerates keyword misspellings by exploiting the indecomposable property of primes. Compared with existing secure fuzzy search schemes, our WMFS scheme has the following merits: 1) Efficiency. It eliminates the requirement of a predefined dictionary and thus supports updates efficiently. 2) High accuracy. It eliminates the false positive and false negative introduced by specific data structures and thus allows the user to retrieve files as accurate as possible. 3) Flexibility. It gives the user great flexibility to specify different search patterns including keyword and substring matching. Extensive experiments on a real data set demonstrate the effectiveness and efficiency of our scheme.

In this paper, we propose a hybrid collaborative filtering recommendation algorithm based on heuristic similarity and trust measure, in order to alleviate the problem of data sparsity, cold start and trust measure. Firstly, a new similarity measure is implemented by weighted fusion of multiple similarity influence factors obtained from the rating matrix, so that the similarity measure becomes more accurate. Then, a user trust relationship computing model is implemented by constructing the user's trust network based on the trust propagation theory. On this basis, a SIMT collaborative filtering algorithm is designed which integrates trust and similarity instead of the similarity in traditional collaborative filtering algorithm. Further, an improved K nearest neighbor recommendation based on clustering algorithm is implemented for generation of a better recommendation list. Finally, a comparative experiment on FilmTrust dataset shows that the proposed algorithm has improved the quality and accuracy of recommendation, thus overcome the problem of data sparsity, cold start and trust measure to a certain extent.