Federated learning (FL) is a new learning paradigm that enables multiple clients to collaboratively train a high-performance model while preserving user privacy. However, the effectiveness of FL heavily relies on the availability of accurately labeled data, which can be challenging to obtain in real-world scenarios. To address this issue and robustly train shared models using distributed noisy labeled data, we propose FedDQ, a noise-robust FL framework that utilizes co-distillation and quality-aware aggregation techniques. FedDQ incorporates two key features: a noise-adaptive training strategy and an efficient label-correcting mechanism. The noise-adaptive training strategy relies on the estimation of labels' noise levels to dynamically adjust clients' training engagement, which mitigates the impact of wrong labels while efficiently exploring features from clean data. In addition, FedDQ designs a two-head network and employs it for co-distillation. The co-distillation strategy facilitates knowledge transfer among clients to share the representational capabilities. Besides, FedDQ enhances label correction to rectify improper labels through co-filtering and label correction. The experimental results demonstrate the effectiveness of FedDQ in improving model performance and handling noisy data challenges in FL settings. On the CIFAR-100 dataset with noisy labels, FedDQ exhibits a notable improvement of up to 32.4% compared to the baseline method.

Intensive communication and synchronization cost for gradients and parameters is the well-known bottleneck of distributed deep learning training. Based on the observations that Synchronous SGD (SSGD) obtains good convergence accuracy while asynchronous SGD (ASGD) delivers a faster raw training speed, we propose Several Steps Delay SGD (SSD-SGD) to combine their merits, aiming at tackling the communication bottleneck via communication sparsification. SSD-SGD explores both global synchronous updates in the parameter servers and asynchronous local updates in the workers in each periodic iteration. The periodic and flexible synchronization makes SSD-SGD achieve good convergence accuracy and fast training speed. To the best of our knowledge, we strike the new balance between synchronization quality and communication sparsification, and improve the tradeoff between accuracy and training speed. Specifically, the core components of SSD-SGD include proper warm-up stage, steps delay stage, and the novel algorithm of global gradient for local update (GLU). GLU is critical for local update operations by using global gradient information to effectively compensate for the delayed local weights. Furthermore, we implement SSD-SGD on MXNet framework and comprehensively evaluate its performance with CIFAR-10 and ImageNet datasets. Experimental results show that SSD-SGD can accelerate distributed training speed under different experimental configurations, by up to 110% (or 2.1× of the original speed), while achieving good convergence accuracy.

With the mobile cloud storage services, mobile users can easily form a group and share data with each other. Given the fact that the cloud are not trustable, a third party public auditor can be introduced to audit data integrity, and supporting group dynamics and protecting the privacy of the original user of shared data from the public auditor is a fundamental issue during the auditing. In this paper, we propose a new identity privacy-preserving public auditing scheme for the integrity of group data with efficient group dynamics utilizing the multilinear maps based Diffie-Hellman Key Exchange protocol. With our proposed scheme, a third party auditor is able to audit the integrity of shared data without learning private identity information of the group members, and proxy re-signatures are used here to allow the cloud to do the re-computing to support group dynamics (user join and user revocation). Besides, our scheme also supports secure and efficient public auditing due to our improved polynomial-based authentication tags. The security and performance analysis shows that our proposed scheme is secure and highly efficient.

Understanding graph characteristics is of great importance for graph analytics. Among the many properties, shortest path distance is the fundamental and widely used one. With the advent of cloud computing, it is a natural choice for the data owners to host their massive graphs on the cloud and outsource the shortest distance querying service to it. However, the new paradigm brings serious security concerns as graph data and shortest distance queries may contain sensitive information of data owners and users. In this paper, we propose a novel scheme to support privacy-preserving approximate shortest distance queries with advanced graph analytics over large-scale encrypted graphs, which enables an untrusted cloud to answer shortest distance queries as well as advanced graph metrics (e.g., node centrality) without knowing the content of queries and the sensitive information of outsourced graphs. Compared with the state-of-the-art solutions, our design can support not only efficient and accurate shortest distance approximation, but also advanced graph analytics. We prove that our scheme is secure under the chosen-plaintext model. Experimental results over real-world datasets show that our scheme achieves high approximation accuracy with practical efficiency.

With cloud services, users can easily host their data in the cloud and retrieve the part needed by search. Searchable encryption is proposed to conduct such process in a privacy-preserving way, which allows a cloud server to perform search over the encrypted data in the cloud according to the search token submitted by the user. However, existing works mainly focus on textual data and merely take numerical spatial data into account. Especially, geometric range search is an important queries on spatial data and has wide applications in machine learning, location-based services(LBS), computer-aided design(CAD), and computational geometry. In this paper, we proposed an efficient and generalized symmetric-key geometric range search scheme on encrypted spatial data in the cloud, which supports queries with different range shapes and dimensions. To provide secure and efficient search, we extend the secure kNN computation with dynamic geometric transformation, which dynamically transforms the points in the dataset and the queried geometric range simultaneously. Besides, we further extend the proposed scheme to support sub-linear search efficiency through novel usage of tree structures. We also present extensive experiments to evaluate the proposed schemes on a real-world dataset. The results show that the proposed schemes are efficient over encrypted datasets and secure against the curious cloud servers.

To protect the privacy of cloud data, searchable encryption is proved to be an important technique since it enables cloud users to search on encrypted data. Existing solutions for searchable encryption mainly focus on some basic search functions such as boolean search, similarity search or limited wildcard-based search. They cannot properly support the advanced search type: structured queries with generalized pattern matching (such as SQL-like queries) which is widely used for information retrieval in cloud database. In this paper, we propose a new searchable encryption scheme that realizes Structured queries with generalized Pattern matching to Search over Encrypted cloud data (SPSE). In particular, SPSE allows users to conduct generalized pattern matching queries on textual attribute values of structured data, and joint them with logical operators (AND, OR, NOT) to search over multiple attributes of the data sets. Besides the improvement of search functionalities, SPSE enhances the privacy by introducing two-tier encryption structure for data confidentiality and by hiding the search pattern of attribute fields to resist statistic analysis from untrusted parties. Security analysis proves that SPSE is KPA-secure. Experiments over real data sets show that SPSE achieves high search accuracy and practical search efficiency.

Solving large-scale systems of linear equations (L-SLE) is a common scientific and engineering computational task. But such problem involves enormous computing resources, which is burdensome for the resource-limited clients. Cloud computing enables computational resource-limited clients to economically outsource such problems to the cloud server. However, outsourcing LSLE to the cloud brings great security concerns and challenges since the LSLE usually contains sensitive information. Previous works for secure outsourcing LSLE are mainly based on iterative methods which cause heavy computation cost for the client side. And they usually neglect to protect the number and position privacy of zero elements in the coefficient matrix, which is not secure enough for many applications. In this paper, with a series of disguise-based techniques, we propose a new efficient and non-iterative algorithm for securely outsourcing LSLE. Our algorithm only requires two rounds of communication between the client and cloud. Furthermore, the number and positions of zero elements in coefficient matrix can be hidden from the cloud with low computational complexity. Finally, we provide extensive theoretical analysis and experimental evaluation to show its high-efficiency and security compared to the previous works.

Searchable encryption is an important and challenging issue. It allows people to search on encrypted data. This is a very useful function when more and more people choose to host their data in the cloud and the cloud server is not fully trustable. Existing solutions for searchable encryption are only limited to some simple functions of search, such as boolean search or similarity search. In this paper, we propose a scheme for Generalized Pattern-matching String-search on Encrypted data (GPSE) in cloud systems. GPSE allows users to specify their search queries by using generalized wildcard-based string patterns (such as SQL-like patterns). It gives users great expressive power in specifying highly targeted search queries. In the framework of GPSE, we particularly implemented two most commonly used pattern matching search functions on encrypted data, the substring matching and the longest-prefix-first matching. We also prove that GPSE is secure under the known-plaintext model. Experiments over real data sets show that GPSE achieves high search accuracy.

Fuzzy keyword search is an important and necessary functionality for information retrieval in modern cloud storage services, since cloud users may submit queries with typos errors or have deficient knowledge about the underlying keywords of cloud data sets. However, for the purpose of privacy preservation, data is usually encrypted before outsourcing to the cloud, which greatly compromises the data utilization flexibility and efficiency. In this paper, we propose F2SE as a novel fuzzy keyword search scheme over encrypted cloud data. Using keyword fingerprint extraction and secure kNN encryption, F2SE can achieve a top-k ranked fuzzy keyword search according to the keyword similarity. Meanwhile, F2SE can return keywords containing special sub strings customized by cloud users with deficient background knowledge, which can be used for exploratory search or uncertain search. Thorough security analysis shows F2SE is KPA-secure while extensive experiments over real data sets demonstrate that F2SE has a low memory overhead and practical searching time cost.