Federated learning (FL) enables a large number of clients to collaboratively train a global model through sharing their gradients in each synchronized epoch of local training. However, a centralized server used to aggregate these gradients can be compromised and forge the result in order to violate privacy or launch other attacks, which incurs the need to verify the integrity of aggregation. In this work, we explore how to design communication-efficient and fast verifiable aggregation in FL. We propose VeriFL, a verifiable aggregation protocol, with O(N) (dimension-independent) communication and O(N+d) computation for verification in each epoch, where N is the number of clients and d is the dimension of gradient vectors. Since d can be large in some real-world FL applications (e.g., 100K), our dimension-independent communication is especially desirable for clients with limited bandwidth and high-dimensional gradients. In addition, the proposed protocol can be used in the FL setting where secure aggregation is needed or there is a subset of clients dropping out of protocol execution. Experimental results indicate that our protocol is efficient in these settings.

During the last few years, the speaker recognition technique has been widely attractive for its extensive application in many fields, such as speech communications, domestics services, and smart terminals. As a critical method, the Gaussian mixture model (GMM) makes it possible to achieve the recognition capability that is close to the hearing ability of human in a long speech. However, the GMM is failing to recognize a short utterance speaker with a high accuracy. Aiming at solving this problem, in this paper, we propose a novel model to enhance the recognition accuracy of the short utterance speaker recognition system. Different from traditional models based on the GMM, we design a method to train a convolutional neural network to process spectrograms, which can describe speakers better. Thus, the recognition system gains the considerable accuracy as well as the reasonable convergence speed. The experiment results show that our model can help to decrease the equal error rate of the recognition from 4.9% to 2.5%.

Searchable symmetric encryption (SSE) has been widely applied in the encrypted database for queries in practice. Although SSE is powerful and feature-rich, it is always plagued by information leaks. Some recent attacks point out that forward privacy which disallows leakage from update operations, now becomes a basic requirement for any newly designed SSE schemes. However, the subsequent search operations can still leak a significant amount of information. To further strengthen security, we extend the definition of forward privacy and propose the notion of “forward search privacy”. Intuitively, it requires search operations over newly added documents do not leak any information about past queries. The enhanced security notion poses new challenges to the design of SSE. We address the challenges by developing the hidden pointer technique (HPT) and propose a new SSE scheme called Khons, which satisfies our security notion (with the original forward privacy notion) and is also efficient. We implemented Khons and our experiment results on large dataset (wikipedia) show that it is more efficient than existing SSE schemes with forward privacy.

Federated learning is a collaborative machine learning framework where a global model is trained by different organizations under the privacy restrictions. Promising as it is, privacy and robustness issues emerge when an adversary attempts to infer the private information from the exchanged parameters or compromise the global model. Various protocols have been proposed to counter the security risks, however, it becomes challenging when one wants to make federated learning protocols robust against Byzantine adversaries while preserving the privacy of the individual participant. In this article, we propose a differentially private Byzantine-robust federated learning scheme (DPBFL) with high computation and communication efficiency. The proposed scheme is effective in preventing adversarial attacks launched by the Byzantine participants and achieves differential privacy through a novel aggregation protocol in the shuffle model. The theoretical analysis indicates that the proposed scheme converges to the approximate optimal solution with the learning error dependent on the differential privacy budget and the number of Byzantine participants. Experimental results on MNIST, FashionMNIST and CIFAR10 demonstrate that the proposed scheme is effective and efficient.

Data deduplication and public auditing are significant for providing secure and efficient network storage services. However, the existing data deduplication schemes supporting auditing not only cannot effectively alleviate the threats of the single point of failure and duplicate-faking attack, but also have to bear the massive waste of computation and storage resources caused by metadata redundancy and repetitive audit tasks. In this paper, we propose a blockchain-based secure deduplication and shared auditing scheme in decentralized storage. Specifically, our scheme utilizes a novel deduplication protocol based on the double-server storage model to achieve efficient space-saving while protecting data users from losing data under a single point of failure and duplicate-faking attack. Besides, it sharply reduces the computation and storage costs of metadata by introducing a lightweight authenticator generation algorithm and update protocol. On this basis, our scheme further adopts a blockchain-based two-way shared auditing mechanism to achieve decentralized public auditing without the third-party auditor, in which the audit authenticators and results of outsourced data are shared among its users to avoid repetitive audit tasks. Security and performance analysis indicates the practicability of our scheme.

Federated learning allows a large number of resource-constrained clients to train a globally-shared model together without sharing local data. These clients usually have only a few classes (categories) of data for training, where the data distribution is non-iid (not independent identically distributed). In this paper, we put forward the concept of category privacy for the first time to indicate which classes of data a client has, which is an important but ignored privacy goal in the federated learning with non-iid data. Although secure aggregation protocols are designed for federated learning to protect the input privacy of clients, we perform the first systematic study on category inference attack and demonstrate that these protocols cannot fully protect category privacy. We design a differential selection strategy and two de-noising approaches to achieve the attack goal successfully. In our evaluation, we apply the attack to non-iid federated learning settings with various datasets. On MNIST, CIFAR-10, AG\_news, and DBPedia datasets, our attack achieves >90% accuracy measured in F1-score in most cases. We further consider a possible detection method and propose two strategies to make the attack more inconspicuous.