摘要：
Classic deep learning methods for human activity recognition (HAR) from wearable sensors struggle with cross-person and cross-position challenges due to nonidentical data distributions caused by context variations (e.g., user, sensor placement). Existing solutions show promise but usually require extensive labeled data from source and target contexts, which is often unavailable in real-world scenarios. To address these limitations, we introduce semi-supervised context agnostic representation learning without target (SCAGOT), a novel semi-supervised approach that learns context-agnostic activity representations without relying on target context data. SCAGOT uses a dual-stream architecture with adversarial disentanglement and a contrastive clustering mechanism. This effectively separates context features from context-agnostic activity features, maximizing intraclass compactness and interclass separability in the activity representation space. In addition, a new inverse cross-entropy loss further refines the representations by removing residual context information. Extensive evaluations on four benchmark datasets demonstrate that SCAGOT outperforms state-of-the-art methods in cross-person and cross-position HAR, offering a promising solution for robust real-world activity recognition.
摘要：
Post-deduplication in traditional cloud environments primarily focuses on single-node, where delta compression is performed on the same deduplication node located on server side. However, with data explosion, the multi-node post-deduplication, also called global deduplication, has become a hot issue in research communities, which aims to simultaneously execute delta compression on data distributed across all nodes. Simply setting up single-node deduplication systems on multi-node environments would significantly affect storage utilization and incur secondary overhead from file migration. Nevertheless, existing global deduplication solutions suffer from lower data compression ratios and high computational overhead due to their resemblance detection's inherent limitations and overly coarse granularities. Similar blocks typically have high correlations between sub-blocks; inspired by this observation, we propose IBNR (Intra-Block Neighborhood Relationship-Based Resemblance Detection for High-Performance Multi-Node Post-Deduplication), which introduces a novel resemblance detection based on relationships between sub-blocks and determines the ownership of blocks in entry stage to achieve efficient global deduplication. Furthermore, the by-products of IBNR have shown powerful scalability by replacing internal resemblance detection scheme with existing solutions on practical workloads. Experimental results indicate that IBNR outperforms state-of-the-art solutions, achieving an average 1.99× data reduction ratio and varying degrees of improvement across other key metrics.
期刊：
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING,2025年:1-13 ISSN：1545-5971
作者机构：
[Zhixiong Xie; Wenlong Tian] School of Computer Science and Technology, University of South China, China;[Jianfeng Lu] School of Computer Science and Technology, Wuhan University of Science and Technology, China;[Zhiyong Xu] Math and Computer Science Department, Suffolk University, USA;[Ruixuan Li] School of Computer Science and Technology, Huazhong University of Science and Technology, China;[Weijun Xiao] Electrical and Computer Engineering, Virginia Commonwealth University, USA
摘要：
Detecting similar data is crucial for optimizing file storage and transmission in HTTP protocols and Content Delivery Networks. Traditional MinHash methods encounter significant efficiency challenges due to their reliance on K-shingle structures, resulting in high computational costs and storage requirements. Additionally, these methods expose privacy risks in cloud environments, where sensitive information can be inferred from MinHash signatures. To address both efficiency and security concerns, we propose Horse-MinHash, which integrates a fast, content-defined feature extraction scheme with a non-interactive zero-knowledge proof-based similarity estimation method. Our approach significantly enhances computational efficiency while ensuring robust privacy protection by preventing plaintext exposure. Experimental results demonstrate that Horse-MinHash achieves lower mean squared error in Jaccard similarity estimation and reduces time overhead for average block sizes of 16KB or more, outperforming state-of-the-art methods.
摘要：
Traditional object detection methods usually underperform when locating tiny or small drones against complex backgrounds, since the appearance features of the targets and the backgrounds are highly similar. To address this, inspired by the magnocellular motion processing mechanisms, we proposed to utilize the spatial–temporal characteristics of the flying drones based on spiking neural networks, thereby developing the Magno-Spiking Neural Network (MG-SNN) for drone detection. The MG-SNN can learn to identify potential regions of moving targets through motion saliency estimation and subsequently integrates the information into the popular object detection algorithms to design the retinal-inspired spiking neural network module for drone motion extraction and object detection architecture, which integrates motion and spatial features before object detection to enhance detection accuracy. To design and train the MG-SNN, we propose a new backpropagation method called Dynamic Threshold Multi-frame Spike Time Sequence (DT-MSTS), and establish a dataset for the training and validation of MG-SNN, effectively extracting and updating visual motion features. Experimental results in terms of drone detection performance indicate that the incorporation of MG-SNN significantly improves the accuracy of low-altitude drone detection tasks compared to popular small object detection algorithms, acting as a cheap plug-and-play module in detecting small flying targets against complex backgrounds.
摘要：
Devices and servers in Federated Edge Learning (FEL) are self-interested and resource-constrained, making it critical to design incentives to improve model performance. However, dynamic network conditions raise energy consumption, while data heterogeneity undermines device cooperation. Current research overlooks the interplay between system efficiency and device clustering, resulting in suboptimal updates. To address these challenges, we develop BENCH, a bilateral pricing mechanism consisting of three core rules aimed at incentivizing participation from both devices and servers. Specifically, we first design a reward allocation rule, based on the Rubinstein bargaining model, which dynamically allocates rewards. Theoretically, we derive a closed-form solution for this rule, demonstrating BENCH achieves Nash equilibrium. Secondly, we design a device partitioning rule that leverages modularity to group similar devices, facilitating personalized edge aggregation to accelerate local data adaptation. Thirdly, we design an edge matching rule that employs the Kuhn-Munkres algorithm to balance the load at edge servers, thus minimizing the congestion. Together, these three rules enable hierarchical optimization of pricing and associations, effectively mitigating the impact of dynamic costs and device heterogeneity. Extensive experiments demonstrate BENCH's effectiveness in increasing device participation by 28.81% and improving model performance by 2.66% compared to state-of-the-art baselines.
通讯机构：
[Chen, YX ; Peng, GW; Zhang, Y ] U;Univ South China, Sch Chem & Chem Engn, Lab Optoelect Technol Low Dimens Nanomat, Hengyang 421001, Peoples R China.;Univ South China, Sch Nucl Sci & Technol, Hengyang 421001, Peoples R China.;Univ South China, Sch Resources Environm & Safety Engn, Hengyang 421001, Peoples R China.
关键词：
2e(−)-WOR-H(2)O(2);Density functional theory;Fe(2+)/Fe(3+) interconversion;SPF system;Synergistic oxidation and reduction
摘要：
Simultaneous organic pollutant oxidation and heavy metal ion reduction may enhance ocean and medical wastewater treatment. Here a self-cycling piezo-photocatalytic Fenton (SPF) system was developed using an Na-Sm bimetal-doped layered ferroelectric perovskite SrBi 2 Nb 2 O 9 (NS-SBNO) and Fe 2+ ions. The experimental results and density functional theory calculations demonstrated that bimetal doping induced an enhanced internal electric field, improving electron–hole pair separation and transmission. NS-SBNO exhibited increased adsorption energy and electron transfer capacity of H 2 O, leading to H 2 O 2 production at 497 μmol g −1 h −1 through a two-electron water oxidation reaction without any sacrificial reagent. Furthermore, compared with traditional Fenton systems, the SPF system afforded higher Fe 2+ /Fe 3+ interconversion efficiency and hydroxyl and superoxide radical yields, highlighting the system’s excellent redox capabilities. The SPF system also demonstrated enhanced oxidation and reduction of complex pollutants in wastewater [e.g., BPA, TC, 2, 4-DCP, NOR, LVX, U(VI), and Cr(VI)], demonstrating promising practical applicability.
Simultaneous organic pollutant oxidation and heavy metal ion reduction may enhance ocean and medical wastewater treatment. Here a self-cycling piezo-photocatalytic Fenton (SPF) system was developed using an Na-Sm bimetal-doped layered ferroelectric perovskite SrBi 2 Nb 2 O 9 (NS-SBNO) and Fe 2+ ions. The experimental results and density functional theory calculations demonstrated that bimetal doping induced an enhanced internal electric field, improving electron–hole pair separation and transmission. NS-SBNO exhibited increased adsorption energy and electron transfer capacity of H 2 O, leading to H 2 O 2 production at 497 μmol g −1 h −1 through a two-electron water oxidation reaction without any sacrificial reagent. Furthermore, compared with traditional Fenton systems, the SPF system afforded higher Fe 2+ /Fe 3+ interconversion efficiency and hydroxyl and superoxide radical yields, highlighting the system’s excellent redox capabilities. The SPF system also demonstrated enhanced oxidation and reduction of complex pollutants in wastewater [e.g., BPA, TC, 2, 4-DCP, NOR, LVX, U(VI), and Cr(VI)], demonstrating promising practical applicability.
摘要：
Diagnosis and treatment of endometrial diseases are crucial for women's health. Over the past decade, ultrasound has emerged as a non-invasive, safe, and cost-effective imaging tool, significantly contributing to endometrial disease diagnosis and generating extensive datasets. The introduction of artificial intelligence has enabled the application of machine learning and deep learning to extract valuable information from these datasets, enhancing ultrasound diagnostic capabilities. This paper reviews the progress of artificial intelligence in ultrasound image analysis for endometrial diseases, focusing on applications in diagnosis, decision support, and prognosis analysis. We also summarize current research challenges and propose potential solutions and future directions to advance ultrasound artificial intelligence technology in endometrial disease diagnosis, ultimately improving women's health through digital tools.
期刊：
Journal of Systems Architecture,2025年168:103538 ISSN：1383-7621
通讯作者：
Wenlong Tian
作者机构：
[Zhihuan Yang; Xuming Ye] School of Computer Science and Technology, University of South China, Hengyang, China;School of Physical and Mathematical Sciences, Nanyang Technology University, Singapore;[Ruixuan Li] School of Computer Science and Technology, Huazhong University of Science and Technology, China;[Zhiyong Xu] Department of Mathematics and Computer Science, Suffolk University, USA;[Wenlong Tian] School of Computer Science and Technology, University of South China, Hengyang, China<&wdkj&>School of Physical and Mathematical Sciences, Nanyang Technology University, Singapore
通讯机构：
[Wenlong Tian] S;School of Computer Science and Technology, University of South China, Hengyang, China<&wdkj&>School of Physical and Mathematical Sciences, Nanyang Technology University, Singapore
摘要：
Cloud storage offers flexibility and efficiency for managing personal data, but redundant data across users necessitates optimization. Deduplication techniques help by storing only unique data, improving efficiency. However, verifying data ownership post-deduplication is challenging. Existing Proof of Ownership (PoW) methods rely on interactive communication with the cloud to verify blocks, causing delays and performance issues. Additionally, many PoW designs assume trust that may not align with real-world scenarios. To address these challenges, we propose Nis-PoW, a non-interactive, secure Proof of Ownership for cloud storage. Nis-PoW simplifies ownership verification to a single round, eliminating delays for unverified block information. It also incorporates efficient proof generation and verification using modular exponentiation and the discrete logarithm problem. Unlike prior schemes, Nis-PoW mitigates brute-force, replay, and Man-in-the-Middle attacks without relying on trusted nodes, ensuring better real-world compatibility. Experimental results show that Nis-PoW reduces I/O operation time complexity and accelerates computations, achieving up to 53.6 × and 54.5 × speedups compared to state-of-the-art approaches.
Cloud storage offers flexibility and efficiency for managing personal data, but redundant data across users necessitates optimization. Deduplication techniques help by storing only unique data, improving efficiency. However, verifying data ownership post-deduplication is challenging. Existing Proof of Ownership (PoW) methods rely on interactive communication with the cloud to verify blocks, causing delays and performance issues. Additionally, many PoW designs assume trust that may not align with real-world scenarios. To address these challenges, we propose Nis-PoW, a non-interactive, secure Proof of Ownership for cloud storage. Nis-PoW simplifies ownership verification to a single round, eliminating delays for unverified block information. It also incorporates efficient proof generation and verification using modular exponentiation and the discrete logarithm problem. Unlike prior schemes, Nis-PoW mitigates brute-force, replay, and Man-in-the-Middle attacks without relying on trusted nodes, ensuring better real-world compatibility. Experimental results show that Nis-PoW reduces I/O operation time complexity and accelerates computations, achieving up to 53.6 × and 54.5 × speedups compared to state-of-the-art approaches.
摘要：
Ionic liquids (ILs) have emerged as new persistent pollutants in aquatic environments due to their notable ecotoxicity. Herein, In 2 Se 3 @Ag 3 PO 4 S-scheme piezo-photocatalyst with interfacial In-O and Se-P covalent bonds is prepared for efficient degradation of 1-butyl-2,3-dimethylimidazole bromide ([BMMIm]Br). The experimental results demonstrate that 98.3 % of [BMMIm]Br is degraded under piezo-photocatalysis. Notably, [BMMIm]Br functions as a hole sacrificial agent, leading to a simultaneous H 2 production rate of 582.7 μmol g −1 h −1 and a co-removal efficiency of 97.2 % for radioactive heavy metal ions of U(VI), achieving the "three birds with one stone" effect. Density functional theory (DFT) calculations indicate that the S-scheme structure, combined with the In-O and Se-P covalent bonds and the piezoelectric effect, effectively promotes the separation of electron/hole pairs while inhibiting carrier recombination dynamics, thereby enhancing piezo-photocatalytic performance. Moreover, systemic toxicity evaluations, including assessments of calculated toxicity, zebrafish growth, and bean sprout development, were conducted to verify the reduced toxicity of the degraded intermediates, highlighting the potential practical applications of this approach.
Ionic liquids (ILs) have emerged as new persistent pollutants in aquatic environments due to their notable ecotoxicity. Herein, In 2 Se 3 @Ag 3 PO 4 S-scheme piezo-photocatalyst with interfacial In-O and Se-P covalent bonds is prepared for efficient degradation of 1-butyl-2,3-dimethylimidazole bromide ([BMMIm]Br). The experimental results demonstrate that 98.3 % of [BMMIm]Br is degraded under piezo-photocatalysis. Notably, [BMMIm]Br functions as a hole sacrificial agent, leading to a simultaneous H 2 production rate of 582.7 μmol g −1 h −1 and a co-removal efficiency of 97.2 % for radioactive heavy metal ions of U(VI), achieving the "three birds with one stone" effect. Density functional theory (DFT) calculations indicate that the S-scheme structure, combined with the In-O and Se-P covalent bonds and the piezoelectric effect, effectively promotes the separation of electron/hole pairs while inhibiting carrier recombination dynamics, thereby enhancing piezo-photocatalytic performance. Moreover, systemic toxicity evaluations, including assessments of calculated toxicity, zebrafish growth, and bean sprout development, were conducted to verify the reduced toxicity of the degraded intermediates, highlighting the potential practical applications of this approach.
摘要：
Recently, Oblivious Storage has been proposed to prevent privacy leakage from user access patterns, which obfuscates and makes it computationally indistinguishable from the random sequences by fake accesses and probabilistic encryption. The same data exhibits distinct ciphertexts. Thus, it seriously impedes cloud providers' efforts to improve storage utilization to remove user redundancy, which has been widely used in the existing cloud storage scenario. Inspired by the successful adoption of removing duplicate data in cloud storage, we attempt to integrate obliviousness, remove redundancy, and propose a practical oblivious storage, PEO-Store. Instead of fake accesses, introducing delegates breaks the mapping link between a valid access pattern and a specific client. The cloud interacts only with randomly authorized delegates. This design leverages non-interactive zero-knowledge-based redundancy detection, discrete logarithm problem-based key sharing, and secure time-based delivery proof. These components collectively protect access pattern privacy, accurately eliminate redundancy, and prove the data delivery among delegates and the cloud. Theoretical proof demonstrates that, in our design, the probability of identifying the valid access pattern with a specific client is negligible. Experimental results show that PEO-Store outperforms state-of-the-art methods, achieving an average throughput of up to 3 times faster and saving 74% of storage space.
摘要：
The concept of data locality is crucial for distributed systems (e.g., Spark and Hadoop) to process Big Data. Most of the existing research optimized the data locality from the aspect of task scheduling. However, as the execution container of Spark's tasks, the executor launched on different nodes can directly affect the data locality achieved by the tasks. This article tries to improve the data locality of tasks by executor allocation in Spark framework. First, because of different communication modes at stages, we separately model the communication cost of tasks for transferring input data to the executors. Then formalize an optimal executor allocation problem to minimize the total communication cost of transferring all input data. This problem is proven to be NP-hard. Finally, we present a greed dropping heuristic algorithm to provide solution to the executor allocation problem. Our proposals are implemented in Spark-3.4.0 and its performance is evaluated through representative micro-benchmarks (i.e., WordCount, Join, Sort) and macro-benchmarks (i.e., PageRank and LDA). Extensive experiments show that the proposed executor allocation strategy can decrease the network traffic and data access time by improving the data locality during the task scheduling. Its performance benefits are particularly significant for iterative applications.
作者机构：
[Ye, Xuming; Tian, Wenlong; Yang, Zhihuan] Univ South China, Sch Comp Sci & Technol, Hengyang, Peoples R China.;[Tian, Wenlong] Nanyang Technol Univ, Sch Phys & Math Sci, Singapore, Singapore.;[Li, Ruixuan] Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan, Peoples R China.;[Xu, Zhiyong] Suffolk Univ, Dept Math & Comp Sci, Boston, MA USA.
会议名称：
2024 IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
会议时间：
17 December 2024
会议地点：
Sanya, China
会议主办单位：
[Yang, Zhihuan;Tian, Wenlong;Ye, Xuming] Univ South China, Sch Comp Sci & Technol, Hengyang, Peoples R China.^[Tian, Wenlong] Nanyang Technol Univ, Sch Phys & Math Sci, Singapore, Singapore.^[Li, Ruixuan] Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan, Peoples R China.^[Xu, Zhiyong] Suffolk Univ, Dept Math & Comp Sci, Boston, MA USA.
会议论文集名称：
2024 IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
关键词：
Proof of Ownership;Cloud Storage;Discrete Logarithm Problem;Privacy-Preserving
摘要：
Cloud storage is widely used for flexible and efficient data management, yet redundant data across users requires storage optimization. Deduplication helps by storing only unique data, making data sharing and ownership verification essential post-deduplication. Current Proof of Ownership (PoW) methods rely on interactive communication, leading to delays and performance issues during intensive data operations, and often assume a level of trust that may not hold in practical scenarios. To overcome these issues, we propose ES-PoW, a non-interactive secure proof of ownership scheme for cloud storage. ES-PoW performs ownership verification in a single round, avoiding delays in block verification. Using modular exponentiation and the discrete logarithm problem, ES-PoW generates and verifies ownership proofs efficiently. Unlike previous schemes, ES-PoW is resilient against brute-force, replay, and Man-in-the-Middle attacks, without relying on trusted nodes, making it better suited to real-world applications. Experimental results show that ES-PoW reduces I/O operation time and accelerates computation, achieving up to 53.6× and 54.5× speed improvements over current methods.
摘要：
U-network is a comprehensive convolutional neural network that is widely utilized in medical image segmentation domain. However, it is not accurate enough in detail segmentation and resulting in unsatisfactory segmentation results. To solve this problem, this paper proposes an enhanced U-network that combines an improved Pyramid Pooling Module (PPM) and a modified Convolutional Block Attention Module (CBAM). Its whole network is U-Net architecture, where the PPM is improved by reducing the number of bin species and increasing the pooling connection multiples. It is used in the downsampling part of the network, which can extract input image features of various dimensions. And the CBAM is modified by using $1\times 1$ convolutional layers instead of the original fully connected layers. It is used in the upsampling part of the network, which can combine convolution and attention mechanism. This pays attention to the image from two aspects of space and channel. Besides, the network is trained with novel RGB training to further improve the segmentation ability of the network. Experimental results show that our network outperforms traditional U-shaped segmentation networks by 30% to 40% in metrics Dice, IoU, MAE, and BFscore respectively. What‘s more, it is better than U-Net ++, U2-Net, ResU-Net, ResU-Net++, and UNeXt in terms of segmentation effect and training time.
作者机构：
[Tian, Wenlong; Yang, Zhihuan] Univ South China, Sch Comp Sci & Technol, Hengyang, Peoples R China.;[Tian, Wenlong] Nanyang Technol Univ, Sch Phys & Math Sci, Singapore, Singapore.;[Zhang, Emma] Needham High Sch, Needham, MA USA.;[Xu, Zhiyong] Suffolk Univ, Math & Comp Sci Dept, Boston, MA USA.
会议名称：
2024 IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
会议时间：
17 December 2024
会议地点：
Sanya, China
会议主办单位：
[Yang, Zhihuan;Tian, Wenlong] Univ South China, Sch Comp Sci & Technol, Hengyang, Peoples R China.^[Tian, Wenlong] Nanyang Technol Univ, Sch Phys & Math Sci, Singapore, Singapore.^[Zhang, Emma] Needham High Sch, Needham, MA USA.^[Xu, Zhiyong] Suffolk Univ, Math & Comp Sci Dept, Boston, MA USA.
会议论文集名称：
2024 IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
关键词：
Cloud Storage;Encrypted Data Reduction;Zero-Knowledge Proof
摘要：
With the widespread adoption of cloud storage, effectively identifying and eliminating redundant data among users while ensuring data security has become a significant challenge. However, traditional similarity detection methods has limitations in privacy protection. Although conventional encryption techniques can safeguard privacy, they have difficulty detecting redundancy between similar blocks. Thus, we propose a secure reduction of redundant and similar data for cloud storage to address these challenges based on zero-knowledge proof (Sec-Reduce), called Sec-Reduce. It first employs a novel zero-knowledge proof technique for file-level redundancy detection, where redundant files are identified and excluded from storage. To further determine the similarity of non-redundant files, the scheme performs content-based chunking and feature extraction using a similarity feature extraction method. These extracted features are then encrypted using the approximate homomorphic encryption scheme Cheon-Kim-Kim-Song (CKKS) to enable similarity detection in the ciphertext environment. Finally, secure delta encoding is applied to store unique ciphertext blocks and deltas. Evaluations of real-world datasets demonstrate that Sec-Reduce achieves higher storage savings than existing encrypted storage methods, with storage overhead comparable to plaintext storage and only moderate performance overhead.
期刊：
2023 IEEE 22ND INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS, TRUSTCOM, BIGDATASE, CSE, EUC, ISCI 2023,2024年:833-840 ISSN：2324-898X
通讯作者：
Tian, WL
作者机构：
[Ye, Xuming; Tian, Wenlong; Wang, Jinzhao; Wan, Yaping] Univ South China, Sch Comp Sci & Technol, Hengyang, Peoples R China.;[Tian, Wenlong] Nanyang Technol Univ, Sch Phys & Math Sci, Singapore, Singapore.;[Li, Ruixuan] Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan, Peoples R China.;[Tang, Junwei] Wuhan Text Univ, Sch Comp Sci & Artificial Intelligence, Wuhan, Peoples R China.;[Xu, Zhiyong] Suffolk Univ, Math & Comp Sci Dept, Boston, MA 02114 USA.
通讯机构：
[Tian, WL ] U;Univ South China, Sch Comp Sci & Technol, Hengyang, Peoples R China.;Nanyang Technol Univ, Sch Phys & Math Sci, Singapore, Singapore.
会议名称：
2023 IEEE 22nd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
会议时间：
01 November 2023
会议地点：
Exeter, United Kingdom
会议主办单位：
[Wang, Jinzhao;Tian, Wenlong;Ye, Xuming;Wan, Yaping] Univ South China, Sch Comp Sci & Technol, Hengyang, Peoples R China.^[Tian, Wenlong] Nanyang Technol Univ, Sch Phys & Math Sci, Singapore, Singapore.^[Li, Ruixuan] Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan, Peoples R China.^[Tang, Junwei] Wuhan Text Univ, Sch Comp Sci & Artificial Intelligence, Wuhan, Peoples R China.^[Xu, Zhiyong] Suffolk Univ, Math & Comp Sci Dept, Boston, MA 02114 USA.
会议论文集名称：
2023 IEEE 22nd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
摘要：
With the increasing number of big data applications, large amounts of valuable data are distributed in different organizations or regions. Federated Learning (FL) enables collaborative model training without sharing sensitive data and is widely used in AI medical diagnosis, economy, and autonomous driving scenarios. However, it still leaks the privacy from the gradient exchange in federated learning. What's worse, state-of-the-art work, such as Batchcrypt, still suffers from computational overhead due to a considerable amount of computation and communication costs caused by homomorphic encryption. Therefore, we propose a novel symmetric key-based homomorphic encryption scheme, Sym-Fed. To unleash the power of symmetric encryption in federated learning, we combine random masking with symmetric encryption and keep the homomorphic property during the gradient exchange in the federated learning process. Finally, the security analysis and experimental results on real workloads show that our design achieves performance improvement 6x to 668x and reduces the communication overhead 1.2x to 107x compared with the state-of-the-art work, BatchCrypt and FATE, without model accuracy degradation and security compromise.
摘要：
Smart meters are part of the Advanced Measurement Infrastructure (AMI) system in the smart grid. It facilitates data transfer between consumers and electricity suppliers (ES). However, the mass deployment of smart meters (SM) brings heavy overhead to grid operation and poses serious privacy threats. To this end, this paper proposes a secure and efficient data aggregation scheme of cloud–edge collaboration smart meters. At first, we standardize the users’ historical electricity load features and use the improved K-Means clustering algorithm to calculate the Euclidean distance between feature vectors to obtain the classification results of users’ load features. On this basis, ES generates relevant parameters to encrypt meter data and protect users’ data privacy based on classification results. The aggregator (Ag) performs the data aggregation, generates the overall signature using the Schnorr aggregation signature method, and sends it to the cloud server (CS). The ES queries the CS to obtain data and parses it to realize the customer billing service. Meanwhile, this paper executes a series of experiments, and the results show that the proposed scheme exhibits significant advantages in privacy protection and system operation efficiency.
Smart meters are part of the Advanced Measurement Infrastructure (AMI) system in the smart grid. It facilitates data transfer between consumers and electricity suppliers (ES). However, the mass deployment of smart meters (SM) brings heavy overhead to grid operation and poses serious privacy threats. To this end, this paper proposes a secure and efficient data aggregation scheme of cloud–edge collaboration smart meters. At first, we standardize the users’ historical electricity load features and use the improved K-Means clustering algorithm to calculate the Euclidean distance between feature vectors to obtain the classification results of users’ load features. On this basis, ES generates relevant parameters to encrypt meter data and protect users’ data privacy based on classification results. The aggregator (Ag) performs the data aggregation, generates the overall signature using the Schnorr aggregation signature method, and sends it to the cloud server (CS). The ES queries the CS to obtain data and parses it to realize the customer billing service. Meanwhile, this paper executes a series of experiments, and the results show that the proposed scheme exhibits significant advantages in privacy protection and system operation efficiency.
摘要：
<jats:p>It is crucial to detect high-severity defects, such as memory leaks that can result in system crashes or severe resource depletion, in order to reduce software development costs and ensure software quality and reliability. The primary cause of high-severity defects is usually resource scheduling errors, and in the program source code, these defects have contextual features that require defect context to confirm their existence. In the context of utilizing machine learning methods for defect automatic confirmation, the single-feature label method cannot achieve high-precision defect confirmation results for high-severity defects. Therefore, a multi-feature fusion defect automatic confirmation method is proposed. The label generation method solves the dimensionality disaster problem caused by multi-feature fusion by fusing features with strong correlations, improving the classifier’s performance. This method extracts node features and basic path features from the program dependency graph and designs high-severity contextual defect confirmation labels combined with contextual features. Finally, an optimized Support Vector Machine is used to train the automatic detection model for high-severity defects. This study uses open-source programs to manually implant defects for high-severity defect confirmation verification. The experimental results show that compared with existing methods, this model significantly improves the efficiency of confirming high-severity defects.</jats:p>
