How to automatically recognize the bird species has caused concerns in ecological systems and intelligent ecological monitoring system due to the increasing threat to bird ecological society and bird species diversity. However, traditional monitoring systems are susceptible to specific challenges when operating in complex environments, such as complex environments, multifarious postures and backlight scenarios. To effectively address these challenges, we present a novel bird ecological intelligent detection system (TransSIL) for fine-grained bird image classification (FBIC) in diverse ecological to learn discriminative features by explicitly incorporating silhouette structural information alongside critical visual cues. Specifically, the approach begins with a silhouette token construction module to estimate the bird silhouette and extract silhouette tokens. Then, a silhouette relationship mining module is developed to fuse visual and silhouette tokens and capture long-range dependencies between them. In addition, to learn bird distinctive features at multiple levels, a critical cues awareness module is embedded within TransSIL. The performance of TransSIL was evaluated on two bird datasets: CUB200-2011 and NABirds. The framework demonstrates significant improvements over existing ecological intelligent surveillance methods. By utilizing silhouette and visual dependencies, we anticipate that our approach will ultimately contribute to the conservation of avian ecological societies.

With the growth of cloud computing infrastructure, its cost-efficient paradigm is driving a growing wave of small and medium-sized enterprises to migrate data and services to cloud based platforms. However, due to privacy concerns, data encryption prior to outsourcing is an important means of protection, which in turn requires performing queries over the encrypted data. While several approaches do offer support for privacy preserving skyline or top-k queries, they typically struggle with efficiency when extended to secure top-k dominating queries, due to the inherent nature of combining the advantages of both top k and skyline queries. Nevertheless, this nature renders them as a more practical and promising alternative for location-based services. To address this, we introduce STLD, a secure top-k location-based dominating query scheme. Specifically, we develop an innovative index structure called Secure Aggregate R-tree (SAR-tree) by utilizing the Paillier cryptosystem and introducing meticulously crafted noise, while also incorporating principles from aggregate R-trees and semi-blind R-trees. Leveraging this structure, we propose a series of secure sub-protocols to facilitate top-k dominating queries, accompanied by optimization techniques to mitigate latency associated with computationally intensive dominating operations. Given an encrypted query, STLD not only efficiently answers the query but also guarantees the privacy of data(sets), results, queries and access patterns. Finally, STLD undergoes rigorous theoretical security and complexity analysis, complemented by empirical evaluations that demonstrate its performance and feasibility, achieving a reduction in query cost by 40%-60% compared to multiple competing methods.

How to recognize endangered bird species in complex outdoor environments has attracted considerable attention in the fields of computer vision and machine learning. However, fine-grained bird image classification (FBIC) is susceptible to problems such as arbitrary postures, interclass discriminability, and occlusions. We propose a novel semantic homology relationship representation learning for fine-grained bird classification with large language models, namely HomLLM, to address these challenges in FBIC effectively. Our proposed model aims to learn homology relationship representations adaptively by identifying invariant structural correspondences between visual features and semantic descriptions, using limited bird data and base class labels. Our approach yields two key findings: 1) invariant homology in key regions of birds that maintain structural consistency across different postures and 2) homological relationship that establish essential taxonomic markers among similar bird classes. Based on these insights, we propose two new modules of the model: the semantic homology generation (SHG) module and homology relationship mining (HRM) module. Specifically, in SHG, bird features are described at multiple granularities through a large language model (LLM) to establish semantic homology. In HRM, feature adaptation is performed separately for textual and visual information, and cross-modal homological interaction is performed hierarchically. In addition, we propose a hierarchical homology interaction scheme to integrate multilevel homological features while preserving structural consistency. Experiments on the commonly used bird datasets CUB-200-2011 and NABirds demonstrate that HomLLM exhibits better performance than state-of-the-art (SOTA) methods.

ABSTRACT Differential privacy is a widely recognized approach for enhancing privacy in federated learning by preventing sensitive information leakage during model training and deployment. These mechanisms typically bound the sensitivity of model updates through gradient or model parameter clipping, followed by noise injection to achieve formal privacy guarantees. However, achieving stronger privacy guarantees necessitates more noise, which can adversely impact model utility. Although various clipping and noise‐adding mechanisms have been explored in client‐level differential privacy, their comparative effectiveness within hierarchical federated learning remains underexplored. This study addresses this gap by systematically evaluating three primary clipping and noise‐adding approaches within a three‐tier hierarchical federated learning framework. The evaluation was conducted using two distinct neural networks trained on federated datasets derived from benchmark datasets. Each mechanism was assessed under three different noise levels, with performance measured by test accuracy and convergence behavior across global rounds. The results indicate that front‐loaded differential privacy mechanisms, such as clipping gradients and adding noise to either the clipped gradients or model parameters, achieve better convergence and model utility across varying noise scales and data distributions than the approach based on clipping and perturbing model parameter differences. These findings are particularly relevant to real‐world applications in privacy‐sensitive hierarchical settings, such as edge computing in healthcare and finance, where balancing privacy and utility is essential.

With the swift advancement of the Internet of Things (IoT) and artificial intelligence (AI), various technologies have been integrated into wearable medical health devices, improving users’ awareness of their physical states and enabling the analysis of a greater amount of human data. However, these sensitive pieces of information are prone to tampering or theft during storage and transmission, posing security risks. In this article, we propose a multiattribute sketch secure data sharing scheme for IoT wearable medical devices based on blockchain (MASS). We introduce a multiattribute sketch storage method that stores the encrypted hash of health data transmitted by medical wearable devices on the blockchain. This work also designs a ciphertext-policy attribute-based encryption (CP-ABE) access control mechanism that effectively addresses the secure sharing of data from wearable medical devices among healthcare professionals. Experimental findings indicate that with the rise in the number of medical health data documents, the costs associated with index generation and search time decrease by 55.3% and 10.83%, respectively. Additionally, as the frequency of data access increases, there is a 13.5% reduction in encryption time, and the implementation of multiattribute sketches results in a 24.8% and 11.3% reduction in index generation and search times, respectively.

With the rapid growth of encrypted image data outsourced to cloud servers, achieving data confidentiality and searchability in cloud-assisted Internet of Things (IoT) environments has become increasingly feasible. However, achieving high efficiency and strong security simultaneously over large-scale encrypted image datasets remains a challenge. To address this, we propose a novel efficient and secure content-based image retrieval scheme in cloud-assisted IoT. Specifically, our scheme leverages lattice-based fully homomorphic encryption and homomorphic comparison techniques, utilizing Cheon-Kim–Kim-Song’s batch processing and single-instruction-multiple-data capabilities. This approach significantly reduces the overhead of fully homomorphic computations, making the query process computational complexity independent of dataset size under certain conditions. Moreover, by integrating private information retrieval technology, the scheme enhances privacy by hiding access patterns of image data. Formal security analysis demonstrates that our scheme achieves indistinguishability against chosen-plaintext attack (IND-CPA), and extensive experiments based on real datasets confirm that our scheme is both practical and efficient for real-world applications.

Secure inference is the main technology to avoid privacy leakage when reasoning with machine learning models. The existing secure inference schemes have been widely explored in the academic field, but when the neural network model is large, existing solutions based on Trusted Execution Environments (TEE) must be configured with a large number of trusted devices due to insufficient hardware memory, which incurs high deployment costs. In addition, existing homomorphic encryption schemes have a high computational cost for ciphertexts, which incurs high time cost when the model is large. To address these issues, we propose a low time overhead secure inference scheme by training a generative adversarial network, which can reduce the calculations for ciphertext. We also use a trusted execution environment to compute nonlinear functions in neural networks, which solves the problem of high computational cost for nonlinear functions in HE while suppressing the growth of noise in HE. Security analysis proves that our scheme achieves semi-honest security, and extensive experiments demonstrate that our scheme has lower time overhead in large neural networks when compare with previous solutions.

Federated learning (FL) has attracted increasing attention in recent years due to its data privacy preservation and great applicability to large-scale user scenarios. However, when FL faces numerous clients, it is inevitable to emerge the non-independent and identically distributed (non-iid) data between clients, which brings an enormous challenge for model training and performance analysis like convergence. Besides, due to the non-iid data, the participating clients of FL tend to be extremely heterogeneous so the number of samplings among clients causes a sampling variance problem, which induces a huge variation in convergence. More importantly, although FL can foster privacy security via locally retaining the training data, if local data is secret and sensitive, FL should have more powerful privacy protection to resist the cloud server or third party to infer private information from shared models or intermediate gradients. Facing the non-iid and privacy challenges, we propose a differential privacy (DP) based non-iid FL algorithm called DPNFL to jointly tackle these two issues. Specifically, motivated by the DP and its variants, we are the first to adopt the truncated concentrated differential privacy technique under the FL scenario to more tightly track end-to-end privacy loss, while requiring less noise injection for the same level of DP. To avoid the sampling variance problem, we enable the server to sample the partial clients uniformly without replacement, which also guarantees unbiased sampling. To further improve the algorithm performance, we also propose an adaptive version of DPNFL named AdDPNFL, which adopts the adaptive optimization on the server-side to simultaneously alleviate the impact of non-iid data and DP noise on model utility. Finally, we perform extensive experiments to validate the effectiveness and superiority of our algorithms.

This paper considers online convex optimization (OCO) with generated i.i.d. stochastic constraints, where the performance is measured by adaptive regret. The stochastic constraints are disclosed at each round to the learner after the decision is made. Different from the previous non-adaptive constrained OCO algorithm which is directly generalized from the static online gradient descent algorithm, we propose the novel Virtual Queue-based Following-the-Leader-History (VFLH) strategy to make the constrained OCO algorithm adaptive. In this framework, the algorithm generalizes experts that deal with the static constrained optimization problem within specified time intervals. Subsequently, it combines the predictions of active experts to produce a final choice and unify the average regret and constraints virtual queue. The algorithm’s performance is evaluated based on two metrics: the bounds of constraint violation and regret. To address the difficulty of proving the constraint violation bound under the adaptive setting, we first employ the multi-objective drift analysis approach to handle the constraints virtual queue. Further analysis of the regret bound and the numerical results also supports the performance of the newly proposed algorithm.

Deep learning (DL) has been adopted in a broad range of Internet-of-Things (IoT) applications such as auto-driving, intelligent healthcare and smart grids, but limitations such as those relating to data and user privacy can complicate its broader implementation. Seeking to jointly address both privacy and utility, in this paper we connect the layer-wise relevance propagation with gradient descent for injecting proper noise into gradients. We also improve the conventional gradient clipping method by dividing the gradients into several groups; thus, minimizing the gradient distortion. Since the noisy gradient causes the undetermined descent direction and might adversely affect the loss minimization, we use the NoisyMin algorithm to select the best step size for each gradient perturbation. Finally, we integrate the adaptive optimizer into the gradient descent. In addition to improving the model utility, we also leverage the leading Sinh-Normal noise addition mechanism to achieve truncated concentrated differential privacy (tCDP) – as demonstrated by our rigorous analysis. Our experimental evaluations also validate the effectiveness of the proposed algorithm.