Abstract Industry 4.0 leverages information and intelligent technologies to create a highly flexible production model that supports personalized and digital products and services. However, stringent privacy protection requirements have resulted in the fragmentation and inaccessibility of production data across various companies, creating a significant data barrier. Federated learning (FL) effectively addresses privacy concerns during the data sharing process and facilitates the collaborative use of industrial production data across various institutions. However, due to the characteristics of the FL training model, attackers can implement reconstruction attacks and attribute inference attacks on the local model or global model to obtain the privacy of the data provider. Additionally, poisoning attacks by malicious users can damage the performance of FL models, thereby affecting the system’s overall utility. Many studies propose new techniques that combine privacy mechanisms and poisoning detection, but most solutions rely on outlier detection and introduce additional risks, making them impractical for real-world applications. To address these issues, we propose a privacy-preserving FL optimization method capable of resisting highly concealed poisoning attacks, FedCPA. Specifically, we protect the local model by adding eliminable noise, allowing the server to perform secure aggregation based on the fuzzy model. Furthermore, we design a ciphertext-based, two-layer architecture poisoning model detection algorithm to defend against highly concealed poisoning attacks such as Sybil attacks. Finally, the correctness of the entire calculation process is calculated and proven.

The integration of blockchain-based federated learning (BFL) and Industry 4.0 utilizes intermediate models to execute task deployment and result acceptance, effectively solving the problems of data barriers and data resource waste in Industry 4.0. However, the BFL ecosystem is susceptible to poisoning and inference attacks that undermine data privacy and model security. In this paper, we propose PSFL, a robust FL framework that guarantees both data privacy and model security. Specifically, we design a cross-validation algorithm where numerous participants conduct a thorough assessment of the user’s contribution growth rate in the current round. This approach proves effective in identifying Byzantine attackers engaged in malicious activities within the system. Furthermore, we propose a lightweight multi-receiver signcryption mechanism employing secure key distribution, which significantly minimizes resource overhead. Finally, the security of PSFL is proved based on the random oracle model. Empirical assessment affirms the effectiveness and practicality of PSFL, even with different proportions of malicious users, PSFL’s performance is 10%20% higher than Trimmed Mean and M-Krum. In summary, PSFL improves the model accuracy and the security of the model transmission process in scenarios involving edge node poisoning, which demonstrates that PSFL can be well adapted to Industry 4.0.

Federated Learning (FL) allows clients to keep local datasets and train collaboratively by uploading model gradients, which achieves the goal of learning from fragmented sensitive data. Although FL prevents clients’ datasets from being shared directly, local private information may be leaked through gradients. To mitigate this problem, we combine game theory to design an FL scheme (IMFL) based on the incentive mechanism and differential privacy (DP). Firstly, we explore three DP variants, all of which are resistant to deep leakage from gradients (DLG) but differ in their level of privacy protection. In addition, we perform the convergence analysis of the FL model based on DP. Then, with the assistance of game theory, we analyze the natural state of the server and clients in the FL process and formulate the utility function of both sides under the case of considering the attack. Finally, we establish the optimization problem as a Stackelberg game and solve for the optimal strategy of the server and clients by deriving the Nash equilibrium to achieve personalized protection. Theoretical proof demonstrates that both types of entities can achieve optimal actions by maximizing their utility functions upon reaching the Nash equilibrium. Besides, extensive experiments are conducted on real-world datasets to demonstrate that the IMFL is efficient and feasible.

Using federated learning (FL) to train global models in IoT improves computational efficiency and protects users’ data privacy. However, FL still faces privacy threats. Driven by interests, servers reduce their computational cost or induce wrong decisions in IoT devices by returning wrong global model gradients. Although the verifiability of aggregation results is achieved in previous research, it is difficult to defend against collusion attacks launched by servers and users. Therefore, we construct a rational verifiable federated learning secure aggregation protocol based on the dual-server framework and game theory, which achieves verifiable aggregation results, and effectively defends against collusion attacks. Firstly, we propose a new model verification code based on the property of irreversible matrices, which allows users to verify the correctness of the aggregation results by matrix products. This model validation code is computationally efficient and resistant to the adversary’s backward inference. Secondly, we adopt a dual-server architecture and improve the prisoner contract and betrayal contract according to the actual application scenarios of IoT, converting the previous collusion attacks between servers and users to collusion attacks between servers and making the rational servers not launch collusion attacks to destroy the verification mechanism of the aggregation results through the incentive mechanism. Finally, we demonstrate through security analysis that RVFL is secure and effective against collusion and reverse inference attacks. In addition, we show through experimental results that RVFL can improve its efficiency by three orders of magnitude in the verification phase and 88% in the masking phase.

Federated learning of deep neural networks has emerged as an evolving paradigm for distributed machine learning, gaining widespread attention due to its ability to update parameters without collecting raw data from users, especially in digital healthcare applications. However, the traditional centralized architecture of federated learning suffers from several problems (e.g., single point of failure, communication bottlenecks, etc.), especially malicious servers inferring gradients and causing gradient leakage. To tackle the above issues, we propose a robust and privacy-preserving decentralized deep federated learning (RPDFL) training scheme. Specifically, we design a novel ring FL structure and a Ring-Allreduce-based data sharing scheme to improve the communication efficiency in RPDFL training. Furthermore, we improve the process of distributing parameters of the Chinese residual theorem to update the execution process of the threshold secret sharing, supporting healthcare edge to drop out during the training process without causing data leakage, and ensuring the robustness of the RPDFL training under the Ring-Allreduce-based data sharing scheme. Security analysis indicates that RPDFL is provable secure. Experiment results show that RPDFL is significantly superior to standard FL methods in terms of model accuracy and convergence, and is suitable for digital healthcare applications.

Abstract As an important approach to overcome data silos and privacy concerns in deep learning, federated learning, which can jointly train the global model and keep data local, has shown remarkable performance in a range of industrial applications. However, federated learning still suffers from the problem that shared gradients may be subject to tampering, inference functions, and falsification. To address this issue, we propose a verifiable federated learning framework to deal with malicious aggregators. Initially, we propose a reputation calculation mechanism to solve the problem of selecting a reliable aggregator based on a multiweight subjective logic model. Furthermore, we design a verifiable federated learning scheme to ensure data confidentiality, integrity, and verifiability, as well as support the client's dynamic withdrawal. Security analyses indicate that our framework is secure against malicious adversaries. Furthermore, experimental results on real datasets show that our verifiable federated learning has high accuracy and feasible efficiency.

Federated learning breaks down data silos and promotes the intelligence of the Industrial Internet of Things (IIoT). However, the principal–agent architecture commonly used in federated learning not only increases the cost but also fails to take into account the privacy protection and trustworthiness of flexible on-demand data sharing. To tackle the above challenges, we propose a secure and trusted federated data sharing (STFS) based on blockchain. Initially, we construct an autonomous and reliable federated extreme gradient boosting learning algorithm to crack the data isolation problem, providing privacy protection and verifiability. Furthermore, we design a secure and trusted data sharing and trading mechanism to ensure secure on-demand controlled data sharing and fair trading. Finally, the security of STFS is proved based on the universal composable theory. The results of ample experimental simulations demonstrate the good effectiveness and performance of STFS for IIoT applications.

Benefiting from the development of smart urban computing, the mobile crowd sensing (MCS) network has emerged as momentous communication technology to sense and collect data. The users upload data for specific sensing tasks, and the server completes the aggregation analysis and submits to the sensing platform. However, users’ privacy may be disclosed, and aggregate results may be unreliable. Those are challenges in the trust computation and privacy protection, especially for sensitive data aggregation with spatial information. To address these problems, a verifiable location-encrypted spatial aggregation computing (LeSAC) scheme is proposed for MCS privacy protection. In order to solve the spatial domain distributed user ciphertext computing, firstly, we propose an enhanced-distance-based interpolation calculation scheme, which participates in delegate evaluator based on Paillier homomorphic encryption. Then, we use aggregation signature of the sensing data to ensure the integrity and security of the data. In addition, security analysis indicates that the LeSAC can achieve the IND-CPA indistinguishability semantic security. The efficiency analysis and simulation results demonstrate the communication and computation overhead of the LeSAC. Meanwhile, we use the real environment sensing data sets to verify availability of proposed scheme, and the loss of accuracy (global RMSE) is only less than 5%, which can meet the application requirements.

The requirement for data sharing and privacy has brought increasing attention to federated learning. However, the existing aggregation models are too specialized and deal less with users’ withdrawal issue. Moreover, protocols for multiparty entity matching are rarely covered. Thus, there is no systematic framework to perform federated learning tasks. In this paper, we systematically propose a privacy‐preserving federated learning framework (PFLF) where we first construct a general secure aggregation model in federated learning scenarios by combining the Shamir secret sharing with homomorphic cryptography to ensure that the aggregated value can be decrypted correctly only when the number of participants is greater than t. Furthermore, we propose a multiparty entity matching protocol by employing secure multiparty computing to solve the entity alignment problems and a logistic regression algorithm to achieve privacy‐preserving model training and support the withdrawal of users in vertical federated learning (VFL) scenarios. Finally, the security analyses prove that PFLF preserves the data privacy in the honest‐but‐curious model, and the experimental evaluations show PFLF attains consistent accuracy with the original model and demonstrates the practical feasibility.