Rejoining fragment images of precious artifacts is a meaningful task because complete artifacts could provide valuable clues for the research of human civilization. However, existing rejoining methods face several challenges including time-consuming manual annotation, insufficient rejoining accuracy, and prohibitive computation cost. For rejoining fragment images of bone sticks (a precious artifact), we propose a lightweight vision graph neural network called RejoinViG to address these challenges. First, our method avoids time-consuming manual annotation of ballast contour data by experts. Specifically, our method directly takes a pair of fragment images as input and then determines whether the image pair is rejoinable. Second, our method improves rejoining accuracy by contour, script, and texture through dynamically constructing local and global graphs. Third, our method improves rejoining accuracy while reducing computation cost by introducing a new attention mechanism named node self-attention. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods significantly. For example, the Top-1 accuracy of our method is 3.9 times that of SFF-Siam. Surprisingly, our method successfully rejoins a pair of previously unknown but rejoinable fragment images of bone sticks in a real-world scenario.

With the popularity of federated learning, federated domain generalization (FedDG) has attracted more and more attention. Existing works of federated learning indicate that the generalization performance of the global model can be improved when the global model is obtained by aggregating local models according to suitable weights. However, existing methods to calculate weights do not fully utilize the data influences on the global model update, which gives us an opportunity to improve the generalization performance of the global model further. In this paper, we propose the method DI (data influences), which utilizes data influences on the global model update to calculate dynamical weights of local model in each round of training. Specifically, the first component data influence calculator (DIC) of DI calculates local weights of local model from the influences of data on the global model update and we introduce the influence function to complete the calculation process. The second component data influence adjuster (DIA) of DI calculates global weights (which are used in the aggregation process of the global model) from local weights. Extensive experiments indicate that our method improves the generalization performance of models significantly. In particular, our method improves model accuracy on benchmark datasets PACS, OfficeHome, and Office-31 by 1.79%, 1.61%, and 2.39% on average, respectively. Source code is publicly available at github-https://github.com/zikunZHOUHH/Fed-DI.

Skin diseases are one of the most common diseases worldwide, and the mismatch between skin disease patients and dermatologists leads to a huge waste of healthcare resources. Accurately matching skin disease patients to appropriate dermatologists by an image-based method of skin disease recognition can reduce the waste of healthcare resources. However, existing image-based methods of skin disease recognition do not fully utilize multi-source and multi-scale features, which leaves us the chance to improve skin disease recognition further. In this paper, we propose a fusion method of multi-source image features and multi-scale image features to improve skin disease recognition. First, we design a fusion module of multi-source image features to integrate multi-source image information. By dual Convolutional Block Attention Module (CBAM) blocks, the fusion module of multi-source image features enhances the feature representation of key regions and then obtains a comprehensive representation of skin diseases. Second, we propose a fusion module of multi-scale image features. By two parallel backbone networks, the fusion module of multi-scale image features can extract deep feature representations from different scales and exploit their complementarity. To validate the effectiveness of our method, we conduct extensive experiments. The experiment results demonstrate that our method outperforms the state-of-the-art method, achieving improvements of 6.30%, 12.52%, 10.85%, 12.16%, and 5.06% in accuracy, precision, recall, F1-score, and AUC, respectively.

With the popularity of federated learning, federated domain generalization (FedDG) has attracted more and more attentions. Existing works of federated learning indicate that the generalization performance of the global model can be improved when the global model is obtained by aggregating local models according to a suitable weights. However, the existing methods to calculate weights do not fully utilize the data influences on the global model update, which gives us an opportunity to improve the generalization performance of the global model further. In this paper, we propose the method DI (data influences), which utilizes the data influences on the global model update to calculate dynamical weights of local model in each round of training. Specifically, the first component data influences calculator (DIC) of DI calculates the local weights of local model from the influences of each data on the global model update and we introduce the influences function to complete the calculation process. The second component data influences adjuster (DIA) of DI calculates the global weights (which are used in the aggregation process of the global model) from local weights. Extensive experiments indicate that our method improves the generalization performance of models significantly. In particular, our method improves model accuracy on benchmark datasets PACS, OfficeHome, and Office-31 by 1.79%, 1.61%, and 2.39% on average, respectively. Source code is publicly available at github.

Betweenness centrality is one of the key centrality measures in many applications including community detections in biological networks, vulnerability detections in communication networks, misinformation filtering in social networks, etc. The top-$K$group betweenness centrality problem is to find a group of$K$nodes from a network so that the total fraction of shortest paths that pass through the$K$nodes is maximized. Existing studies proposed randomized sampling algorithms for the problem. We notice that the existing studies ensured that, the maximum deviation of the estimated centrality of every group from its expectation is no greater than a small given threshold for all potential groups with no more than$K$nodes, thereby generating too many samples, as the number of such groups is prohibitively large. In contrast, in this paper we first devise a novel algorithm that enables to estimate the centrality of a tentative group adaptively, and the algorithm immediately stops once the centrality is large enough; otherwise, the algorithm uses more samples to find a better group. We then theoretically show that, even the algorithm uses much less samples, it still can find a performance-guaranteed group with a large success probability. Experimental results with real-world networks demonstrate that the number of samples used by the proposed algorithm is from 2 to 18 times smaller than the state-of-the-art, while the centrality of the group found by the algorithm is no more than 4% smaller than the latter.

Differential privacy (DP) is introduced into many fields of AI to preserve privacy. However, introducing DP into AI models is extremely error-prone. To verify whether DP AI models can provide privacy guarantee (quantified by privacy budget) as these models claim, existing methods utilize attack methods to audit whether privacy budget of these models is the same as these models claim. To further improve precision of privacy budget auditing, we propose a brand new way to audit privacy budget, namely directly utilizing the parameters of DP AI models to audit privacy budget. In particular, our method utilizes statistical characteristics variance of the output distribution of DP mechanism to audit privacy budget of DP mechanism. DP AI models are regarded as data samples from output distribution of DP AI model training method and are utilized to approximate the variance of output distribution. The approximated variance is leveraged to estimate the variance of noise distribution of DP mechanism and through the relationship between noise variance and privacy budget, our method calculates the audited privacy budget through estimated noise variance. In addition, to reduce computation overhead, our method constructs parameter selection strategy to identify position whose parameter is suitable for privacy budget auditing. Comprehensive experiments are conducted to verify the effectiveness of our auditing method. Comparison results of five competitive auditing methods demonstrate that our method decreases MAE by 18.29% and decreases MSE by 23.17% on experiment datasets.

Auditing the privacy budget of differential privacy (DP) artificial intelligence (AI) models is necessary to ensure that industrial data are protected at the desired level by DP mechanisms. However, existing auditing methods are not general and precise enough to deal with various kinds of AI models, because the existing auditing methods require customizing audit frameworks and utilize information from model parameters insufficiently. In this article, we propose aprecise andgeneral method toauditthe privacy budget of DPAImodels precisely. Our method associates the parameters of the DP AI model with privacy budget through the Bayesian perspective, achieving tight auditing results with a limited number of DP AI models. Extensive experiments show that our method is more precise and general than existing methods. In particular, the experiments involve ten different datasets, five different models, and three different ways to achieve differential privacy, which indicates the generality of our method. According to empirical experiment results, in 35 out of 36 comparison experiments, our method demonstrates improvements in precision.

Currently, no practical lightweight authenticated key agreement (AKA) protocol with fine-grained pre-authentication has been developed to address security issues such as data integrity, authenticity, traceability, tamper-proofing, and privacy in 5G NR V2X. In this paper, we introduce a lightweight anonymous attribute-based signature of knowledge (Lw-AABSoK) scheme built on Curve25519 to defend against key-leakage attacks. This scheme enables attribute revocation and online credential updating, serving as a fine-grained pre-authentication cryptographic module for V2X secure communication. Leveraging the proposed Lw-AABSoK, we design an end-to-end fine-grained pre-authenticated key agreement protocol (E2E-FGpAKA). The E2E-FGpAKA is UDP-compatible; all interactive messages are self-validated by the Lw-AABSoK, and their sizes are strictly below the 5G NR MAC Transport Block Size (TBS). Through rigorous comparative analysis, scientific experimental verification, and comprehensive evaluation, it is evident that the proposed scheme holds significant practical value for 5G NR V2X.

UAVs (Unmanned Aerial Vehicles) are promising tools for efficient data collections of sensors in IoT networks. Existing studies exploited both spatial and temporal data correlations to reduce the amount of collected redundant data, in which sensors are first partitioned into different clusters, a master sensor in each cluster then collects raw data from other sensors and compresses the received data. An energy-constrained UAV finally collects the maximum amount of compressed data from different master sensors. We however notice that the compressed data from only a portion of clusters are collected by the UAV in the existing studies, while the data from other clusters are not collected at all. In this paper, we study a problem of finding a data collection trajectory for an energy-constrained UAV, so that the accumulative utility of collected data is maximized, where the accumulative utility measures the quality of spatiotemporally correlated data collected from different clusters. We propose a novel 16+-approximation algorithm for the problem, where is a given constant with >0. Experimental results with real datasets show that the accumulative utility by the proposed algorithm is at least 23% larger than those by the existing studies, and the number of clusters collected by the proposed algorithm is from 45% to 105% larger than those by the existing studies.

Authenticated Key agreement protocol (AKA) is one of the essential components for reliable secure communication in Industrial Internet-of-Things (IIoT) communication model. Recently, Srinivas et al. proposed a three-factor elliptic curve cryptosystem (ECC)-based AKA protocol called UAP-BCIoT for WSN-based intelligent transportation system (ITS). In this paper, we first find out that their protocol has a security weak point inherently called master secret disclose and key forgery defect which makes their protocol susceptible to variant impersonation attacks. To overcome the deficiency of their protocol, we construct an improved ECC-based three-factors (credential, password and biometric) tripartite authenticated key agreement protocol among managers Ui, domain gateway DG and IIoT nodes INj with identity dynamic revocation and online updating (IDR-OU-TAKA) for secure communication in IIoT. Unlike the vast majority of previous GWN-assisted MAKA protocols that only negotiate the session key between Ui and INj, our IDR-OU-TAKA protocol can selectively achieve Ui DG INj tripartite key negotiation according to Ui’s IPv6 addresses, meaning that any two parties can use the session key to establish a secure channel which can achieve isolation security within the IIoT domain. Besides, in our proposed IDR-OU-TAKA, the overdue or corrupted manager can be immediately revoked by dynamically maintaining the revocation list and the identity of manager can be securely updated online through an open channel. We give rigorous security proof based on real-or-random (ROR) model and the non-mathematical (informal) security analysis to our proposed IDR-OU-TAKA protocol. Finally, we conduct a comprehensive comparison and evaluation to our proposed IDR-OU-TAKA protocol with other state-of-art MAKA protocols in terms of security and functionality features, communication, and computation costs which clearly indicate that our protocol is more practical and suitable for IIoT.

Unmanned aerial vehicle (UAV)-enabled intelligent systems are emerging and empowering real-time monitoring and modeling tasks. The security requirements in real-time UAV-enabled intelligent systems are data integrity, authenticity, traceability, tamper-proofing, and privacy. A secure channel established by authenticated key agreement (AKA) protocol can cover all the security requirements. However, no UDP-based lightweight pairing-free AKA protocol has been proposed for the UAV system. In this article, we propose a UDP-compatible Curve25519-infrastructural identity-based end-to-end pre-AKA protocol (UDP-IBE2E-pAKA) with system auto-upgrading and direct and lifecycle credential revocation as a lightweight and reliable UDP-based secure communication module for UAV-enabled networks, which perfectly fits the rapid mobility and extremely harsh work environments of UAVs. To protect UAV-enabled systems stable from DDoS attacks, we construct an efficient identity-based signature as a preauthentication mechanism for the verifier to directly authenticate the sender without any redundant operations. In addition, to prevent the corrupted UAV from monitoring and disrupting attacks, our protocol can revoke the malicious entities directly and immediately with a revocation list in the authentication phase. Moreover, online mode auto-upgradable algorithms are designed to achieve key exposure resistance in our protocol. The full proof of the authenticity and privacy are given in this article. The comprehensive comparison with other state-of-the-art end-to-end AKA protocols indicates that our protocol meets the most robustness and highest efficiency on Raspberry Pi 5.

Access control and authenticity are two critical concerns of the encrypted propagating data in edge computing-assisted intelligent transportation systems (EC-ITS). This paper presents a fully traceable and verifiable ciphertext-policy attribute-based encryption scheme with auditable outsourced decryption and dynamic identity revocation (FTV-AOD-DR-CP-ABE) for EC-ITS as a confidential and fine-grained data sharing and acquiring module. The proposed FTV-AOD-DR-CP-ABE is computing-efficient that all the algorithms executed by vehicles including\(\mathbf{Enc}\),\(\mathbf{OutKeyGen}\)and\(\mathbf{FinalDec}\)are constant complexity. In addition, an efficient identity-based signature and message commitment (IBSMC) algorithm is constructed for the ciphertext and message in our FTV-AOD-DR-CP-ABE to provide both of them with traceable authenticity and verifiability. An outsourced key auditing algorithm\(\mathbf{TKAudit}\)is also innovated for RSU to audit the legality and freshness of outsourced key\(\mathsf{TK}\), which can protect the propagating data system against the flooding and DDoS attack with the illegal outsourced keys. Based on the traceability of the ciphertext and outsourced key, a dynamic vehicle revocation mechanism is designed in our scheme. Next the rigorous proofs of the data confidentiality, ciphertext and message traceable verifiability,\(\mathsf{TK}\)auditability and revocable security are given in random oracle model (ROM). Finally, by comprehensive comparison and evaluation of the proposed FTV-AOD-DR-CP-ABE with other state-of-the-art data propagating schemes, our FTV-AOD-DR-CP-ABE is more comprehensive.

With the popularity of artificial intelligence and cloud computing, many neural network models can be placed on the cloud server as an open service, such as Google Goggles and the online face recognition system of Baidu. The data owner sends his data to the cloud server to get the prediction result of data. Obviously, the cloud service provider can access model parameters and private data if there is no additional protection mechanism. On the one hand, if the adversary can access private data, they can freely use the artificial intelligence model and Big Data technologies to analyze the data owner. On the other hand, when the adversary can access model parameters, the interest of model owner would be harmed. Thus, preserving model parameters (model privacy) and private data (data privacy) becomes the key for applying neural network models as open cloud services. In this article, to protect the model privacy and data privacy in neural network prediction even when a cloud service provider colludes with the data owner or the model owner, we first propose a new system model with two no-colluding cloud servers and a corresponding security model. Then, we propose a new non-interactive outsourcing scheme, which can protect model privacy together with data privacy. Our scheme is able to resist collusive attacks of one server and the data owner as well as collusive attacks of one server and the model owner. At last, the security analyses indicate that our scheme just needs no collusion between cloud servers. The performance analyses indicate that our scheme is very lightweight for the data owner, and it is about tens of milliseconds for a neural network model with 1000 parameters.

Summary Due to successful applications of data analysis technologies in many fields, various institutions have accumulated a large amount of data to improve their services. As the speed of data collection has increased dramatically over the last few years, an increasing number of users are growing concerned about their personal information. Therefore, privacy preservation has become an urgent problem to be solved. Differential privacy as a strong privacy preservation tool has attracted significant attention. In this review, we focus on improving data utility of differentially private mechanisms through technologies related to cryptography. In particular, we first focus on how to improve data utility through anonymous communication. Then, we summarize how to improve data utility by combining differentially private mechanisms with homomorphic encryption schemes. Next, we summarize hardness results of what is impossible to achieve for differentially private mechanisms' data utility from the view of cryptography. Differential privacy borrowed intuitions from cryptography and still benefits from the progress of cryptography. To summarize the state‐of‐the‐art and to benefit future researches, we are motivated to provide this review.

Outsourced decryption attribute-based encryption (OD-ABE) is emerging as a promising cryptographic tool to provide efficient fine-grained access control for data accessing and sharing in cloud-assisted Intelligent Internet of Mobile Things (IIoMT). Decryption verification is an essential property of OD-ABE to enable the mobile user to verify the precision of the decryption data. Unfortunately, the most representative verification (commitment) algorithms have various security flaws. In this article, we first indicate that the two state-of-art key-based commitment schemes are vulnerable to “Commitment Extract(Decrypt)-then-Reuse Attack” and “Commitment Impersonation Attack” which demolish the unforgeability of the commitment. Then to cover all the existing attacks to commitment algorithms, we redefine a robuster verifiable security model for verifiable OD-ABE. Subsequently, we invent a ciphertext fingerprint (CTfp)-based commitment scheme and give rigorous proof to the proposed commitment scheme, including binding, hiding, unforgeability, and nonrepudiation (traceability) in the random oracle. Next, we apply our CTfp-based commitment to the widely used OD-ABE schemes to provide them robuster verifiability. Finally, the theoretical comparison and simulation experiments are presented to show our new type of commitment algorithm is more secure and practical.

Massive Internet of Things (IoT) data sets are possessed by big institutions serving daily life because IoT devices are widely used in our daily life such as wearable devices and smart home devices. Publishing these data sets among various institutions causes an increasing number of users to concern their personal privacy. Differential privacy is the state-of-the-art concept of privacy preservation, but it suffers from the low accuracy. In this article, we improve differentially private mechanisms including the Laplace mechanism as well as the sample and aggregation mechanism by bringing the personalized sampling technology into these mechanisms so that IoT data sets can be privately published through differentially private mechanisms. In particular, improved mechanisms assign a personalized sampling probability to each data record in a way that their accuracy can be improved. We analyse improved mechanisms in terms of their privacy and accuracy. Then, we empirically demonstrate that the performance of improved mechanisms is better than original mechanisms through extensive experiments on synthetic data sets and real-world data sets.

Differential privacy is a widely accepted concept of privacy preservation, and the Laplace mechanism is a famous instance of differentially private mechanisms used to deal with numerical data. In this paper, we find that differential privacy does not take the linear property of queries into account, resulting in unexpected information leakage. Specifically, the linear property makes it possible to divide one query into two queries, such as$q(D)=q(D_{1})+q(D_{2})$if$D=D_{1}\cup D_{2}$and$D_{1}\cap D_{2}=\emptyset $. If attackers try to obtain an answer to$q(D)$, they can not only issue the query$q(D)$but also issue$q(D_{1})$and calculate$q(D_{2})$by themselves as long as they know$D_{2}$. Through different divisions of one query, attackers can obtain multiple different answers to the same query from differentially private mechanisms. However, from the attackers’ perspective and differentially private mechanisms’ perspective, the total consumed privacy budget is different if divisions are delicately designed. This difference leads to unexpected information leakage because the privacy budget is the key parameter for controlling the amount of information that is legally released from differentially private mechanisms. To demonstrate unexpected information leakage, we present a membership inference attack against the Laplace mechanism. Specifically, under the constraints of differential privacy, we propose a method for obtaining multiple independent identically distributed samples of answers to queries that satisfy the linear property. The proposed method is based on a linear property and some background knowledge of the attackers. When the background knowledge is sufficient, the proposed method can obtain a sufficient number of samples from differentially private mechanisms such that the total consumed privacy budget can be made unreasonably large. Based on the obtained samples, a hypothesis testing method is used to determine whether a target record is in a target dataset.

The differential privacy is the state-of-the-art conception for privacy preservation due to its strong privacy guarantees, however it suffers from low accuracy. In this paper, we propose a personalized sample Laplace mechanism by combining the Laplace mechanism with sampling technology. In order to improve the accuracy, the proposed mechanism assigns personalized sampling probability to each record. Based on the personalized sampling probability, we prove that the proposed mechanism satisfies ε differential privacy. Then we compare the proposed mechanism with other mechanisms in term of the accuracy. Through extensive experiments on synthetic data set and real world data set, we demonstrate that the performance of proposed mechanism is better.

The logistic model is a very elementary and important model in the field of machine learning. In this article, an efficient differential privacy logistic classification mechanism is proposed. The proposed mechanism is better than object function perturbation mechanism in terms of running time and accuracy. Regarding accuracy, the proposed mechanism's accuracy is almost the same as the no differential privacy (non-dp) mechanism, and the proposed mechanism is better than that of the object function perturbation mechanism in both the test accuracy and the train accuracy. As for the running time of the training model, the proposed mechanism is better than the object function mechanism and is the same as the non-dp mechanism.