In low-altitude economy (LAE) networks, Artificial General Intelligence (AGI) models play a critical role in tasks such as path planning, object recognition, and task allocation. Support Vector Machine (SVM) models serve as fundamental components in AGI frameworks due to their robust capabilities in classification and regression tasks, which are essential for decision-making in LAE networks. However, distributed deployment and real-time inference of SVM models face significant challenges in security and privacy protection, including leakage of model parameters, exposure to data privacy, and reliability of prediction results. To address these issues, we propose a privacy-preserving and verifiable SVM prediction scheme (pvSVM) that can achieve the desirable properties of model privacy, data privacy, and private/public prediction verifiability. To be specific, we employ homomorphic encryption in conjunction with secret sharing to realize efficient and privacy-preserving model prediction in the edge. Then, we design two secure verification strategies to allow UAVs and any third party to check the correctness of predictions. To further support the verification of large-scale predictions, our scheme uses batch verification to reduce computational and communication overheads. Detailed analysis and extensive experiments prove the security and efficiency of our scheme.

With the rapid advancement of ubiquitous connectivity, the Internet of Unmanned Agents (IUA) has emerged as a promising paradigm for distributed intelligent perception and decision-making. In such systems, numerous unmanned agents collaboratively collect environmental data to support coordinated tasks. To preserve data privacy, Federated Learning (FL), as a decentralized machine learning framework, enables collaborative training of a global model across agents without directly exchanging raw data. However, FL faces several critical challenges in IUA environments, including high communication overhead under constrained wireless bandwidth, potential privacy leakage from shared model parameters, and agent dropouts caused by unstable connectivity. To address these challenges, we propose PPE-FL, a privacy-preserving and communication-efficient federated learning scheme designed for IUA scenarios. PPE-FL replaces conventional high-dimensional gradient uploads with lightweight ranking-based votes, substantially reducing communication overhead. Then, we design an obfuscation mechanism to protect the privacy of locally generated ranking-based votes, safeguarding both raw data and intermediate parameters. Furthermore, PPE-FL supports mask reconstruction through partial interactions among online unmanned agents, enabling robust aggregation under dynamic network conditions. Experimental results demonstrate that the proposed PPE-FL reduces communication costs by 89.5% compared to VCD-FL and by 87.7% compared to PPML, while maintaining model accuracy and privacy protection.

Recommendation systems based on graph neural networks (GNNs) have emerged as a promising paradigm due to their ability to capture high-order interactions between users and items. However, in federated scenarios, this advantage is compromised, as each user can access only a first-order subgraph composed of its directly interacted items. To address this issue, most existing solutions introduce a trusted server to assist users in expanding their local subgraphs. However, the server in reality is often untrusted and may deviate from the protocol for its own improper benefit. Furthermore, these solutions primarily focus on the privacy of items while neglecting the privacy of potential relationships between users. To this end, we propose Garland, a GNN-based federated recommendation scheme with malicious security. Garland departs from existing work by ensuring both item and relationship privacy while supporting integrity checks to defend against malicious servers. Specifically, we employ a trending cryptographic primitive of secret-shared shuffle to expand subgraphs in a privacy-preserving and verifiable manner. We also design a pre-shuffle triple-salt encryption mechanism and a post-shuffle user-governed expansion mechanism to reduce communication costs and achieve secure distribution of neighbor information, respectively. Moreover, we develop a secret-shared aggregation mechanism to enable privacy-preserving and verifiable federated training. Theoretical analysis demonstrates the privacy and integrity of Garland. Extensive experimental evaluations on four datasets show that Garland outperforms state-of-the-art solutions.

Personalized federated recommendation systems can not only extract common prior knowledge from extensive decentralized data but also provide personalized models for different users to achieve independent and customized services. Incorporating user relationship graphs to enhance personalized modeling is highly promising in federated recommendation. However, it is challenging to construct such graphs and further capture personalized user information while guaranteeing multi-level (i.e., data-level and edge-level) privacy in reality. To this end, in this paper, we propose P 2 FedRec, a relationship-aware P rivacy-preserving and P ersonalized Fed erated Rec ommendation scheme, which can achieve multi-level privacy protection with personalized modeling guarantees. Specifically, we first develop a user-server collaborative mechanism for relationship graph generation and user-specific preferences capture in a privacy-preserving manner. Then, we design an embedding-shared local graph construction module and a noisy global graph-guided aggregation module to safeguard the data-level and edge-level privacy, respectively. Moreover, we introduce a personalized model training module that enables users to learn tailored local models. Theoretical analysis demonstrates that P 2 FedRec achieves both data-level and edge-level privacy preservation on the user and server sides. Extensive experiments conducted on five real-world datasets highlight the outstanding performance of P 2 FedRec.

Privacy-preserving truth discovery, as a data aggregation algorithm that can extract reliable results from disparate and conflicting data in a privacy-preserving manner, has received a lot of attention in ensuring the reliability and privacy of data in mobile crowdsensing systems. However, most of the existing work requires that workers must stay online all the time during the full process of truth discovery. Although a few recent schemes have been proposed to tolerate worker dropout, they are tailored for a single-round setting. Repeating these schemes several times to adapt to the truth discovery will introduce significant computational and communication overheads, especially for the workers. To solve the above challenges, in this paper, we propose a multi-round efficient and secure truth discovery scheme in mobile crowdsensing systems that can balance the 3-way trade-off between privacy protection, dropout tolerance, and protocol efficiency. Specifically, we devise a novel mask generation capable of reusing secrets to eliminate the costly overhead of workers needing to recompute new secrets each round. Besides, we design a lightweight dropout tolerance mechanism to guarantee that even if workers drop out halfway, the server can still acquire meaningful truth. Rigorous security analysis and extensive experimental results demonstrate the privacy and efficiency of our scheme, respectively.

The neural network has been widely used to train predictive models for applications such as image processing, disease prediction, and face recognition. To produce more accurate models, powerful third parties (e.g., clouds) are usually employed to collect data from a large number of users, which however may raise concerns about user privacy. In this paper, we propose an Efficient and Privacy-preserving Neural Network scheme, named EPNN, to deal with the privacy issues in cloud-based neural networks. EPNN is designed based on a two-cloud model and techniques of data perturbation and additively homomorphic cryptosystem. This scheme enables two clouds to cooperatively perform neural network training and prediction in a privacy-preserving manner and significantly reduces the computation and communication overhead among participating entities. Through a detailed analysis, we demonstrate the security of EPNN. Extensive experiments based on real-world datasets show EPNN is more efficient than existing schemes in terms of computational costs and communication overhead.

With the proliferation of machine learning, the cloud server has been employed to collect massive data and train machine learning models. Several privacy-preserving machine learning schemes have been suggested recently to guarantee data and model privacy in the cloud. However, these schemes either mandate the involvement of the data owner in model training or utilize high-cost cryptographic techniques, resulting in excessive computational and communication overheads. Furthermore, none of the existing work considers the malicious behavior of the cloud server during model training. In this paper, we propose the first privacy-preserving and verifiable support vector machine training scheme by employing a two-cloud platform. Specifically, based on the homomorphic verification tag, we design a verification mechanism to enable verifiable machine learning training. Meanwhile, to improve the efficiency of model training, we combine homomorphic encryption and data perturbation to design an efficient multiplication operation for the encryption domain. A rigorous theoretical analysis demonstrates the security and reliability of our scheme. The experimental results indicate that our scheme can reduce computational and communication overheads by at least 43.94% and 99.58%, respectively, compared to state-of-the-art SVM training methods.