As cloud storage is extensively utilized in the contemporary digital age, assuring data integrity and conserving cloud storage space has become a priority for all. However, existing cross-user deduplication audit schemes conflict with the pay-as-you-go model, causing unnecessary costs and violating data isolation. Moreover, retaining a single copy of identical data across multiple users introduces maintenance challenges during data operations. To address these issues, we propose a new blockchain-enabled efficient deduplication and mixed auditing scheme which intricately integrates Message-Locked Encryption (MLE) to construct Homomorphic Verifiable Tags (HVTs), enabling deduplication without exposing confidential data. Our scheme supports single-user deduplication at both block and file levels, as well as plaintext-ciphertext mixed auditing, thereby preventing redundant payments while preserving data isolation to simplify maintenance during data operations and ownership transfers. By employing Elliptic Curve Cryptography (ECC) to encrypt keys and storing the encrypted keys on the blockchain, we ensure data confidentiality while reducing the burden of local key management. Leveraging blockchain-based smart contracts, we further design a self-auditing mechanism that eliminates reliance on trusted third-party auditors. Moreover, our scheme embraces dynamic data operations through an optimized Merkle Hash Tree (MHT) and enables secure cloud data ownership transfer via identity verification. Finally, we prove the correctness and security of our scheme and evaluate its performance through experiments and comparisons with state-of-the-art works, demonstrating its efficiency, particularly in the data upload phase.

Backdoor attacks cause model misbehaving by first implanting backdoors in deep neural networks (DNNs) during training and then activating the backdoor via samples with triggers during inference. The compromised models could pose serious security risks to artificial intelligence systems, such as misidentifying ‘stop’ traffic sign into ‘80km/h’. In this paper, we investigate the connection characteristic between the backdoor and the trigger in DNNs and observe the fact that the backdoor is implanted via establishing a link between a cluster of neurons, representing the backdoor, and the triggers. Based on this observation, we design LinkBreaker, a new generic scheme for defending against backdoor attacks. In particular, LinkBreaker deploys a neuron consistency check mechanism for identifying compromised neuron set related to the trigger. Then, the LinkBreaker regulates the model to make predictions based on benign neuron set only and thus breaks the link between the backdoor and the trigger. Compared to previous defenses, LinkBreaker offers a more general backdoor countermeasure that is not only effective against input-agnostic backdoors but also source-specific backdoors, which the later can not be defeated by majority of state-of-the-arts. Besides, LinkBreaker is robust against adversarial examples, which, to a large extent, provides a holistic defense against adversarial example attacks on DNNs, while almost all current backdoor defenses do not have such consideration and capability. Extensive experimental evaluations on real datasets demonstrate that LinkBreaker is with high efficacy of suppressing trigger inputs while incurring no noticeable accuracy deterioration on benign inputs.

It is inevitable and evident that outsourcing complicated intensive tasks to public cloud vendors would be the primary option for resource-constrained clients in order to save cost. Unfortunately, the public cloud vendors are usually untrusted. They may inadvertently leak the data or misuse the user’s data, compromise user’s privacy or intentionally corrupt computational results to make the system unreliable. It is therefore important how to stop this happening whilst embracing the computational power of public cloud vendors. Non-negative matrix factorization (NMF) is a significant method for conducting data dimension reduction, which has been widely used in large-scale data processing. Nevertheless, due to its non-polynomial hardness, NMF cannot be conducted efficiently using local computation resources, especially when dealing with big data. Motivated by this issue, we address this by presenting a novel outsourced scheme for NMF (O-NMF), which aims to lessen clients’ computing burden and tackle secure problems faced by outsourcing NMF. Particularly, based on two non-collusion servers, O-NMF exploits Paillier homomorphism to preserve data privacy. Additionally, O-NMF allows a verification mechanism to assist clients in verifying returned results with high probability. Security analysis and experimental evaluation demonstrates that the validity and practicality of O-NMF is also provided in this work.

Deep learning makes the Internet-of-Things (IoT) devices more attractive, and in turn, IoT facilitates the resolution of the contradiction between data collection and privacy concerns. IoT devices with small-scale computing power can contribute to model training without sharing data in collaborative learning. However, collaborative learning is susceptible to generative adversarial network (GAN) attack, where an adversary can pretend to be a participant engaging in the model training and learn other participants' data. In this article, we propose a secure collaborative deep learning model which resists GAN attacks. We isolate the participants from the model parameters, and realize the local model training of participants via the interaction mode, ensuring that neither the participants nor the server would have access to each other's data. In particular, we target convolutional neural networks, the most popular network, design specific algorithms for various functionalities in different layers of the network, making it suitable for deep learning environments. To our best knowledge, this is the first work designing specific protocol against GAN attacks in collaborative learning. The results of our experiments on two real data sets show that our protocol can achieve good accuracy, efficiency, and image processing adaptability.

Due to the complexity of the data environment, many organizations prefer to train deep learning models together by sharing training sets. However, this process is always accompanied by the restriction of distributed storage and privacy. Federated learning addresses this challenge by only sharing gradients with the server without revealing training sets. Unfortunately, existing research has shown that the server could extract information of the training sets from shared gradients. Besides, the server may falsify the calculated result to affect the accuracy of the trained model. To solve the above problems, we propose a privacy-preserving and verifiable federated learning scheme. Our scheme focuses on processing shared gradients by combining the Chinese Remainder Theorem and the Paillier homomorphic encryption, which can realize privacy-preserving federated learning with low computation and communication costs. In addition, we introduce the bilinear aggregate signature technology into federated learning, which effectively verifies the correctness of aggregated gradient. Moreover, the experiment shows that even with the added verification function, our scheme still has high accuracy and efficiency.

Large-scale matrix computation requires a lot of computing resources, but the emergence of cloud computing provides resource-limited users with an economical solution, namely outsourcing computation. Clients can use pay-per-use service of cloud resources to solve complex issues, such as matrix inversion. However, due to the inclusion of privacy information in users' data and the opacity of the calculation operations, clients are in face of the threats of privacy disclosure and fraud. In this paper, we first propose an efficient and secure scheme without precondition for outsourcing large- scale matrix inversion to a public cloud. Compared to the state-of-the-art schemes, our scheme does not require the precondition that the original matrix should be invertible. It relieves clients from checking the invertibility of matrix, which is hard to be implemented with limited resource in reality. Moreover, our scheme can protect clients from being cheated and provide data privacy protection. Experiment results also show that our scheme is highly efficient in practical.

Nowadays, cloud computing is increasingly popular. As its important application, outsourcing has aroused great concern. Modular exponentiation is an expensive discrete-logarithm operation and it is difficult for users to calculate locally. Therefore, securely outsourcing modular exponentiation to cloud is a good choice for resource-limited users to reduce computation overhead. In this paper, to outsource modular exponentiation calculation, we dope out a fully verifiable secure outsourcing scheme with single server, so as to eliminate the collusion attacks which occur in algorithms based on two untrusted servers. Meanwhile, our algorithm allows outsourcers to detect any misbehavior with probability 1, which means the checkability of our algorithm shows a significant improvement in comparison to other single server based schemes. Furthermore, to protect data privacy, we propose a new division method to hide the primitive outsourced data. Compared with the state-of-the-art schemes, our secure outsourcing algorithm has an outstanding performance in both efficiency and checkability.