2026· IEEE Transactions on Information Forensics and Security· Vol 21, pp. 7016-7031· 0 citations· 63 references
Abstract
Decision tree classification serves as a fundamental component in many machine learning applications. As inference services are increasingly outsourced to cloud platforms, designing privacy-preserving mechanisms has become important. To secure outsourced decision tree inference, Chen et al. proposed SecDT, an efficient secret-sharing-based framework. While SecDT offers notable efficiency and preliminary security guarantees, we identify a critical vulnerability: attribute leakage. Specifically, the attributes associated with decision tree nodes are exposed to non-owner parties, which risks revealing sensitive model information. In this paper, we first present two secure enhancements, SecDT+v1 and SecDT+v2. These variants use the transformation matrix technique to obfuscate node attributes within the secret-shared domain. To prevent more advanced leakage through attribute access patterns, we design two advanced variants, SecDT+vH and SecDT+vDP, which incorporate dot-product operations to achieve the attribute-hiding property. Extensive evaluations on real-world datasets demonstrate that our proposed schemes provide robust security guarantees while outperforming state-of-the-art solutions in both classification latency and bandwidth efficiency.
As a classical type of machine learning algorithms, tree models have been widely employed in various fields, such as financial analysis and health diagnostics, offering high-accuracy and low-latency prediction services to users. However, tree evaluation also raises significant privacy concerns, particularly with respect to the tree model and the query sample, while the existing private decision tree evaluation schemes are unable to reach a good trade-off between privacy and efficiency in practice. Therefore, in this paper, we propose an efficient and privacy-preserving tree evaluation scheme based on additive homomorphic encryption, namely PACT. Specifically, PACT introduces an innovative algorithm by leveraging the overflow characteristic of two’s complement to support AHE-based parallel comparison, and it utilizes the lightweight homomorphic addition to select tree paths non-interactively. Meanwhile, we carefully design perturbation and shuffle methods to enhance model and sample privacy. The security of PACT is verified based on the ideal-real paradigm. Experimental results on real-world and synthetic datasets demonstrate the lossless accuracy and superior running efficiency of PACT.
Jiaqi Zhao, Hui Zhu, Junpeng Zhang et al.· IEEE Transactions on Informa...· 0 citations
Attribute-Based Credentials (ABCs) are cryptographic credential systems that enable holders to selectively disclose certified attributes or prove predicates over them, thereby supporting privacy-preserving identity verification while limiting unnecessary information exposure. This paper presents a review of the system model, core security and privacy properties, classification, comparative analysis, and practical deployment challenges of ABCs. It develops a two-dimensional taxonomy consisting of a construction dimension and an extension dimension. The construction dimension covers publicly verifiable signature-based, keyed-verification and MAC-based, and general-purpose ZKP-based ABC constructions, while the extension dimension covers issuer-hiding, threshold and multi-authority, and dynamic-lifecycle ABCs. The resulting comparison shows that these categories exhibit different trade-offs in verifier openness, proof flexibility, privacy guarantees, trust requirements, lifecycle support, and practical deployment requirements. The review further examines key challenges related to the efficiency and scalability of multi-attribute management, privacy-preserving credential lifecycle management, inference risks in selective disclosure, interoperability, post-quantum security, and holder binding. Finally, it synthesizes recent trends and identifies research directions toward efficient, interoperable, privacy-preserving, and practically deployable ABC systems that strengthen digital trust and support trustworthy digital identity infrastructures.
Cloud computing offers organizations scalable storage and computation, but outsourcing data processing to third-party infrastructure introduces serious privacy and confidentiality risks. Two complementary paradigms have emerged to address this challenge: homomorphic encryption (HE), which allows computation directly on encrypted data, and federated learning (FL), which enables collaborative model training without centralizing raw data. This paper presents a structured review of privacy-preserving data processing techniques for cloud environments built on HE and FL, individually and in hybrid combination. We propose a taxonomy of existing approaches, synthesize representative literature in a comparative table, illustrate a generic hybrid HE-FL architecture, and evaluate the two paradigms against criteria including data exposure, computational overhead, communication cost, resistance to inference attacks, and cloud deployment readiness. We further identify open challenges — including computational latency, key management, non-IID data distributions, and standardization gaps — and outline promising directions for future research, such as hardware-accelerated HE, adaptive encryption granularity, and standardized hybrid privacy frameworks for cloud-native machine learning.
Shivendra Shukla, Chandra Shekhar Gautam, Divyansh Tiwari· International Journal of Cre...· 0 citations
In cloud computing environments, data sharing serves as a foundational enabler of collaborative operations across heterogeneous terminals. However, such sharing introduces critical challenges–including privacy leakage, inadequate data security, inflexible access control policies, and substantial computational latency. To address these limitations, this paper proposes a privacy-preserving, secure data-sharing framework tailored for edge-cloud collaborative architectures. Relative to conventional approaches, the proposed framework delivers three principal advancements: (1) User Privacy Protection: We design a secure query-matching algorithm that protects plaintext query keywords during data access. The Cloud Server (CS) performs matching over encrypted trapdoors without directly learning the queried keywords. (2) Computational Efficiency Improvement: Edge Servers (ESs) perform outsourced ciphertext transformation using user-specific transformation keys. The terminal only performs a lightweight local operation to recover the resource. This approach minimizes the computational overhead on the terminal side while safeguarding user privacy, and effectively reduces the overhead associated with user joining and revocation within the same group. (3) Fine-Grained, Policy-Driven Access Control: A cryptographically enforced, attribute- and keyword-aware access control mechanism is implemented, supporting precise, context-sensitive authorization decisions via encrypted keyword search and semantic matching–thereby enhancing both the security posture and operational flexibility of data access control.
Qikun Zhang, Zheng Cai, Jinbo Feng et al.· Journal of King Saud Univers...· 0 citations
Federated learning alleviates data silos through a “data-local, model-global” paradigm, but transmitting plaintext gradients exposes clients to reconstruction attacks from malicious servers. Existing secure aggregation methods face trade-offs among privacy, accuracy, and efficiency: homomorphic encryption incurs high overhead, differential privacy sacrifices accuracy, and lightweight secret-sharing schemes often lack weighted aggregation support and suffer accuracy degradation as client numbers grow. To address these limitations, we propose SecAGG, a lossless secure weighted aggregation scheme based on additive secret sharing. SecAGG adopts a three-tier architecture consisting of client clusters, cooperative servers, and a super server. Clients split weighted model parameters into random shares and distribute them to cooperative servers, which perform encrypted partial aggregation before the super server securely reconstructs the global model. Experimental results demonstrate that SecAGG achieves strict security against up to M-1 colluding servers under the semi-honest model while preserving FedAvg-equivalent accuracy with minimal computation and communication overhead, effectively balancing privacy, accuracy, and efficiency.
Xiaomei Tian· 2026 3rd World Conference on...· 0 citations
A privacy model for searchable symmetric encryption protocols that makes adversarial power a central parameter and induces four privacy levels giving rise to a privacy lattice is proposed, enabling reasoning about how privacy guarantees change under different adversarial capabilities.
Manuela Horduna· Proceedings of the 23rd Inte...· 0 citations