Label differential privacy (Label DP) establishes a rigorous framework for safeguarding sensitive labels in supervised learning scenarios, operating under the premise that instance feature vectors are non-sensitive and publicly accessible. Most existing approaches predominantly rely on randomized flipping that apply uniform probability transformations to convert sensitive labels into privacy-preserved alternatives. However, these methods fail to incorporate the intrinsic structural dependency between instance-level and label-level within the privacy analysis framework, which may suffer significant utility degradation as privacy constraints more tighten. To address these limitations, we make a first attempt to explore the probabilistic generative model for Label DP, where the structured Bayesian nonparametric prior is tailored to capture dependent relationship inherent in instance space through an infinitely deep stick-breaking construction. By explicitly modeling the generative process connecting correlation representations to label distribution, we develop a tailored generative framework that enables principled privacy-utility analysis in Label DP scenarios. Specifically, by treating privacy-preserving learning as an inference task rather than a direct classification problem, our approach leverages the rich structural relationships between instances and labels, allowing for more effective privatization mechanisms that can better handle uncertainty and preserve essential statistical properties while satisfying rigorous privacy guarantees. Comprehensive experiments across multiple benchmark and real-world datasets confirm that our generative modeling framework consistently outperforms previous approaches, maintaining high utility even under strict privacy constraints where earlier methods fail. Code has been available at github11HILADP: https://github.com/hu-yc/HiLaDP.

Federated Distillation (FD) offers significant advantages over conventional Federated Learning (FL) by transmitting model outputs (logits) instead of model parameters, reducing communication costs and supporting heterogeneous model architectures. However, FD systems remain vulnerable to poisoning attacks, where local logits are manipulated to corrupt the global aggregation process. The current defense mechanism, represented by SVAFD, attempts to counter malicious updates using cosine similarity. However, we find that such a method fails to detect subtle perturbations and scale variations in logits. To expose these weaknesses, we propose the Federated Distillation Similarity-Based Attack (FDSA), a three-stage attack comprising peak shuffle, mean regression, and dynamic scaling. FDSA subtly manipulates client logits to evade detection while significantly degrading the robustness of server-side aggregation. By altering class priorities, increasing logit entropy, and dynamically adjusting scaling factors, FDSA maintains high cosine similarity to mask its malicious intent. Experiments on FMNIST and SVHN show that FDSA surpasses five state-of-the-art baseline attacks in reducing model accuracy, with ablation studies confirming its robustness across diverse settings. The source code of this paper is available at https://github.com/SHOWY118/FDSA.

To determine whether images on the crowdsourcing server meet the mobile user’s requirement, an auditing protocol is desired to check these images. However, before paying for images, the mobile user typically cannot download them for checking. Moreover, since mobiles are usually low-power devices and the crowdsourcing server has to handle a large number of mobile users, the auditing protocol should be lightweight. To address the above security and efficiency issues, we propose a novel noninteractive lightweight privacy-preserving auditing protocol on images in mobile crowdsourcing networks, called NLPAS. Since NLPAS allows the mobile user to check images on the crowdsourcing server without downloading them, the newly designed protocol can provide privacy protection for these images. At the same time, NLPAS uses the binary convolutional neural network for extracting features from images and designs a novel privacy-preserving Hamming distance computation algorithm for determining whether these images on the crowdsourcing server meet the mobile user’s requirement. Since these two techniques are both lightweight, NLPAS can audit images on the crowdsourcing server in a privacy-preserving manner while still enjoying high efficiency. Experimental results show that NLPAS is feasible for real-world applications.

The crowdsourcing-based parking reservation system is a new computing paradigm, where private owners can rent their parking spots out. Security is the main concern for parking reservation systems. However, current schemes cannot provide user privacy protection for drivers and have no key agreement functions, resulting in a lot of security problems. Moreover, current schemes are typically based on the time-consuming bilinear pairing and not suitable for real-time applications. To solve these security and efficiency problems, we present a novel security protocol with user privacy called SCPR. Similar to protocols of this field, SCPR can authenticate drivers involved in the parking reservation system. However, different from other well-known approaches, SCPR uses pseudonyms instead of real identities for providing user privacy protection for drivers and designs a novel pseudonym-based key agreement protocol. Finally, to reduce the time cost, SCPR designs several novel cryptographic algorithms based on the algebraic signature technique. By doing so, SCPR can satisfy a number of security requirements and enjoy high efficiency. Experimental results show SCPR is feasible for real world applications.

To simplify the certificate management in public key infrastructure, key management protocols for wireless sensor networks typically use identity-based cryptography for negotiating the shared key. However, current identity-based key management protocols are mainly based on the bilinear map technique, which requires high computation costs on sensor nodes, resulting in short lifetimes of sensor nodes. To address this issue, we present a novel identity-based key management protocol called Identity-Based Key Management using Lagrange Interpolation (IBKML). Similar to the protocols of this field, IBKML can provide confidentiality and integrity protections for the negotiated key. However, compared to other well-known approaches, IBKML is based on Lagrange interpolation instead of bilinear map, which employs only a few modular multiplication operations. Because modular multiplication is much more efficient than bilinear pairing, IBKML can reduce the computation costs on sensor nodes significantly. Experimental results show that the proposed protocol is feasible for real applications. Copyright © 2016 John Wiley & Sons, Ltd.