Blockchain sharding has been deemed a promising solution that can substantially improve blockchain scalability. However, developers must overcome two major technical challenges to implement a sharded blockchain. The first challenge is the high cross-shard transaction ratio in blockchain shards. This issue significantly degrades the throughput of a sharded blockchain. The second challenge is the imbalanced workloads across blockchain shards. In a blockchain with imbalanced workloads, some busy shards have to handle an overwhelming number of transactions and thus become congested. Facing these two challenges, a dilemma is that it is difficult to guarantee a lowcross-shard transaction ratioand maintain thebalanced workloadsacross all shards, simultaneously. We believe that a fine-grained account allocation strategy can address this dilemma. To this end, we formulate the tradeoff between these two metrics as a network-partition problem. We then solve this problem by proposing a sharding protocol, namedShardCutter, which includes the following two crucial components: a community-aware account partition algorithm and a fine-tuned account migration mechanism. Finally, experimental results demonstrate that the proposed protocol outperforms other baselines in terms of throughput, makespan, cross-shard transaction ratio, and the workload balance of shards’ transaction pool.

Transferable adversarial examples are known to cause threats in practical, black-box attack scenarios. A notable approach to improving transferability is using integrated gradients (IG), originally developed for model interpretability. In this paper, we find that existing IG-based attacks have limited transferability due to their naive adoption of IG in model interpretability. To address this limitation, we focus on the IG integration path and refine it in three aspects: multiplicity, monotonicity, and diversity, supported by theoretical analyses. We propose the Multiple Monotonic Diversified Integrated Gradients (MuMoDIG) attack, which can generate highly transferable adversarial examples on different CNN and ViT models and defenses. Experiments validate that MuMoDIG outperforms the latest IG-based attack by up to 37.3% and other state-of-the-art attacks by 8.4%. In general, our study reveals that migrating established techniques to improve transferability may require non-trivial efforts.

Vision Transformers (ViTs) have been widely applied in various computer vision and vision-language tasks. To gain insights into their robustness in practical scenarios, transferable adversarial examples on ViTs have been extensively studied. A typical approach to improving adversarial transferability is by refining the surrogate model. However, existing work on ViTs has restricted their surrogate refinement to backward propagation. In this work, we instead focus on Forward Propagation Refinement (FPR) and specifically refine two key modules of ViTs: attention maps and token embeddings. For attention maps, we propose Attention Map Diversification (AMD), which diversifies certain attention maps and also implicitly imposes beneficial gradient vanishing during backward propagation. For token embeddings, we propose Momentum Token Embedding (MTE), which accumulates historical token embeddings to stabilize the forward updates in both the Attention and MLP blocks. We conduct extensive experiments with adversarial examples transferred from ViTs to various CNNs and ViTs, demonstrating that our FPR outperforms the current best (backward) surrogate refinement by up to 7.0% on average. We also validate its superiority against popular defenses and its compatibility with other transfer methods. Codes and appendix are available at https://github.com/RYC-98/FPR.

Federated Learning (FL) has emerged as a promising approach for collaborative machine learning across distributed clients while maintaining data privacy. However, a major challenge in FL is the performance degradation caused by data heterogeneity, as clients often possess data that are non-independent and identically distributed (non-IID). Specifically, during gradient descent-based optimization, the heterogeneous data distribution across clients can cause each local model to converge to a distinct local optimum, leading to poor generalization when aggregating models into a global one. To address this issue, we propose a personalized federated learning method based on Adaptive Layer-wise Parameter Recombination (FedAlr). FedAlr simultaneously considers the retention of model personalization during recombination, the convergence and stability of the recombined model, and performance improvements. It dynamically adjusts the recombination approach and checks nodes based on performance metrics and leverages interlayer similarity to guide the recombination process. This approach enhances the generalization ability of the global model while preserving the unique characteristics of local models. Experimental results show that FedAlr outperforms existing benchmark methods in both IID and non-IID settings.

Image encoder pre-training has experienced a substantial evolution due to contrastive learning, facilitating the extraction of intricate feature representations from unlabeled datasets. Nevertheless, the precise mitigation of the influence of specific data points, particularly in scenarios without labels, remains an inadequately explored issue within this field. This paper proposes CU-Encoder, the first approach aimed at selectively eliminating the impact of a designated ‘class’ from pre-trained encoders in contrastive learning. We also introduce a new evaluation framework that evaluates the unlearning effect, revealing how effectively the influence of the ‘class’ is removed and the model’s generalization capability is maintained. Comprehensive experiments conducted across different models and datasets highlight the effectiveness of CU-Encoder, confirming its capacity to achieve efficient unlearning while maintaining the model’s performance.

Blockchain sharding is a promising solution for scalability but struggles to reach the expected performance due to the high ratio of cross-shard transactions. Account migration has emerged as a critical approach to optimizing shard performance. However, existing migration solutions suffer from inefficient handling of queued withdrawal transactions from a migrating account and inadequate priority mechanism for migration transaction, resulting in prolonged transaction makespan and reduced system throughput. This paper proposes Caravan, a novel blockchain sharding system for optimizing account migration. First, Caravan proposes a transaction aggregation-based migration scheme to efficiently handle withdrawal congestion post-migration. It incorporates a multi-level Merkle tree and cross-shard synchronization protocol to ensure cross-shard security. Second, Caravan presents an economic incentive-driven priority mechanism that motivates miners to perform transaction aggregation and prioritize migration transactions by increasing the associated revenue. Furthermore, its gas recycling strategy enables users to finance migration costs without awareness or extra expenses. Finally, we develop the Caravan prototype, deploy it on Alibaba Cloud, and experiment with real Ethereum transactions. The results show that compared to the state-of-the-art account migration schemes, Caravan significantly mitigates the transaction surge caused by migration, achieving up to a 3.2× throughput improvement and a 65% reduction in transaction confirmation latency. And users share considerable migration costs without extra expenses, significantly reduce system costs. The code for Caravan is available on GitHub.11Caravan are available athttps://github.com/Caravan-project/Caravan.

Feature selection is a critical data preprocessing stage that has been proven beneficial in data mining and machine learning applications. As most current works focus on privacy during the training and inference tasks in machine learning, implementing privacy preservation in preprocessing is a powerful complement. In this paper, we present anefficient andprivacy-preservingfeatureselection protocol (EPFS) based on secure multiparty computation (MPC). We customize a novel method called approximate fixed-point representation to reduce the bitwidth of the sample distribution probability, thereby decreasing communication overhead. We optimize the comparison protocol by reducing the high-order bits of values according to the characteristics of the datasets and design the feature score calculation protocol together with several other MPC-based sub-protocols. We also construct an efficient feature selection workflow to obtain the reduced feature matrix, which avoids the numerous calls of secure comparison and equality test protocols in loops. Experiments on several real-world datasets show that the improved comparison protocol achieves a 29%-53% improvement in runtime and a 6%-32% reduction in communication compared to the general comparison protocol. The optimized feature selection workflow exhibits an upper performance bound, achieving a 38% improvement in runtime compared to prior work. Besides, we implement secure logistic regression training based on the selection features, where the accuracy has improved by an average of 8% compared to training on raw features.

Privacy-preserving online ride-hailing (ORH) services can offer riders and drivers a more enhanced travel experience without disclosing their location privacy. Group ride-sharing is specifically designed for riders undertaking long-distance trips, allowing a group of riders with similar travel plans to share a single taxi. However, the lack of integrated route planning in existing privacy-preserving schemes prevents them from effectively matching riders with the most optimal taxi. In this paper, we propose a privacy-preserving group ride-sharing matching scheme, PGRoute, based on leveled fully homomorphic encryption (LFHE). In PGRoute, we propose a privacy-preserving path planning method and design a fast ciphertext-based distance matrix computation protocol for the key time-consuming modules in it to effectively improve the efficiency. PGRoute can plan routes for groups of riders, determine the optimal boarding order, and match the most suitable taxi while protecting the location privacy of both riders and taxi drivers. Theoretical analysis and experimental results demonstrate that PGRoute is secure and efficient within ORH systems. Compared to previous works, PGRoute reduces the pickup time for a group of riders by a factor of 2.9-$7.5\times $, and achieves 2.7-$6.7\times $higher computational efficiency.

The demand for mobile terminals to participate in data services is increasingly vital. The General Data Protection Regulation (GDPR) has established several principled requirements for data services. Existing studies focusing on data service put emphasis on data privacy and accessibility. However, they face challenges in achieving data forgetability and portability on mobile devices under GDPR and lack consideration of usage control. In this article, we propose ADSS, an app-level data service scheme for mobile devices that can beavailable-but-invisibleand guarantee fine-grained usage control. ADSS addresses the challenges by executing the logic of data usage in the Trusted Execution Environment (TEE) and managing the TEE states (i.e., data usage states) in the blockchain smart contracts. It not only satisfies the requirements of GDPR, ensuring strong security and confidentiality guarantees, but also enables the functionality of “pay-per-use”. We implement a prototype of the ADSS framework based on ARM Trustzone and conduct experimental evaluations. The results demonstrate that our scheme brings high efficiency compared with other data service schemes and exhibits feasibility on mobile-grade devices.

Cross-institutional Electronic Medical Records (EMRs) sharing significantly improves healthcare quality and reduces costs. Current EMRs are often stored on cloud servers and protected by Attribute-based Encryption (ABE) for access control. Cross-institutional sharing allows doctors to request EMRs access from target Healthcare Institutions (HIs) through attribute-based collaboration, enabling flexible and secure access. However, existing collaboration in practical EMRs sharing scenarios suffers from inefficiency, hindering timely access and treatment. This paper proposes an efficient and privacy-preserving data sharing framework for EMRs, called CARE-EMRs. CARE-EMRs enables efficient EMRs data access for doctors across different HIs through an outsourcing mechanism. Furthermore, we designed an improved cryptographic primitive PPD-CP-ABE to serve as the security foundation for CARE-EMRs framework, ensuring privacy of the outsourced process. We prove the security of CARE-EMRs. Performance analysis indicates that it significantly reduces the computation and communication overhead.

Homomorphic Encryption (HE) enhances data security by enabling computations on encrypted data, advancing privacy-focused computations. The BFV scheme, a promising HE scheme, raises considerable performance challenges. Graphics Processing Units (GPUs), with considerable parallel processing abilities, offer an effective solution. In this work, we present an in-depth study on accelerating and comparing BFV variants on GPUs, including Bajard-Eynard-Hasan-Zucca (BEHZ), Halevi-Polyakov-Shoup (HPS), and recent variants. We introduce a universal framework for all variants, propose optimized BEHZ implementation, and first support HPS variants with large parameter sets on GPUs. We also optimize low-level arithmetic and high-level operations, minimizing instructions for modular operations, enhancing hardware utilization for base conversion, and implementing efficient reuse strategies and fusion methods to reduce computational and memory consumption. Leveraging our framework, we offer comprehensive comparative analyses. Performance evaluation shows a 31.9$\times$speedup over OpenFHE running on a multi-threaded CPU and 39.7% and 29.9% improvement for tensoring and relinearization over the state-of-the-art GPU BEHZ implementation. The leveled HPS variant records up to 4$\times$speedup over other variants, positioning it as a highly promising alternative for specific applications.

Matrix computation is a crucial mathematical tool in scientific fields such as Artificial Intelligence and Cryptographic computation. However, it is difficult for resource-limited devices to execute large-scale matrix computations independently. Outsourcing matrix computation (OMC) is a promising solution that engages a cloud server to process complicated matrix computations for resource-limited devices. However, existing OMC schemes lack public verifiability, and thus resource-limited devices cannot verdict the correctness of the computing results. In this paper, for the first time, we propose a smart contract-based OMC scheme that publicly verifies the outsourcing matrix computation results. In our scheme, a smart contract running over the blockchain serves as a decentralized trusted third party to ensure the correctness of the matrix computation results. To overcome the Verifier's Dilemma in the blockchain, we present a blockchain-compatible matrix verification method that decreases the time complexity from$O(n^{3})$to$O(n^{2})$by utilizing a blinding method with the check digit and padding matrices. We make the verification become the form of comparing whether two results are identical rather than naive re-computing. Finally, we perform experiments on Ethereum and ARM Cortex-M4 and give in-depth analysis and performance evaluation, demonstrating our scheme's practicability and effectiveness.

Homomorphic encryption (HE) is a promising technique for privacy-preserving computations, especially the word-wise HE schemes that allow batching. However, the high computational overhead hinders the deployment of HE in real-word applications. GPUs are often used to accelerate execution, but a comprehensive performance comparison of different schemes on the same platform is still missing. In this work, we fill this gap by implementing three word-wise HE schemes BGV, BFV, and CKKS on GPU, with both theoretical and engineering optimizations. We enhance the hybrid key-switching technique, significantly reducing the computational and memory overhead. We explore several kernel fusing strategies to reuse data, resulting in reduced memory access and IO latency, and enhancing the overall performance. By comparing with the state-of-the-art works, we demonstrate the effectiveness of our implementation. Meanwhile, we introduce a unified framework that finely integrates our implementation of the three schemes, covering almost all scheme functions and homomorphic operations. We optimize the management of pre-computation, RNS bases, and memory in the framework, to provide efficient and low-latency data access and transfer. Based on this framework, we provide a thorough benchmark of the three schemes, which can serve as a reference for scheme selection and implementation in constructing privacy-preserving applications.

In 2022, the National Institute of Standards and Technology (NIST) made an announcement regarding the standardization of Post-Quantum Cryptography (PQC) candidates. Out of all the Key Encapsulation Mechanism (KEM) schemes, the CRYSTAL-Kyber emerged as the sole winner. This paper presents another improved version of Plantard arithmetic that could speed up Kyber implementations on two low-end 32-bit IoT platforms (ARM Cortex-M3 and RISC-V) without SIMD extensions. Specifically, we further enlarge the input range of the Plantard arithmetic without modifying its computation steps. After tailoring the Plantard arithmetic for Kyber’s modulus, we show that the input range of the Plantard multiplication by a constant is at least 2.14× larger than the original design in TCHES2022. Then, two optimization techniques for efficient Plantard arithmetic on Cortex-M3 and RISC-V are presented.We show that the Plantard arithmetic supersedes both Montgomery and Barrett arithmetic on low-end 32-bit platforms. With the enlarged input range and the efficient implementation of the Plantard arithmetic on these platforms, we propose various optimization strategies for NTT/INTT. We minimize or entirely eliminate the modular reduction of coefficients in NTT/INTT by taking advantage of the larger input range of the proposed Plantard arithmetic on low-end 32-bit platforms. Furthermore, we propose two memory optimization strategies that reduce 23.50%~28.31% stack usage for the speed-version Kyber implementation when compared to its counterpart on Cortex-M4. The proposed optimizations make the speed-version implementation more feasible on low-end IoT devices. Thanks to the aforementioned optimizations, our NTT/INTT implementation shows considerable speedups compared to the state-of-the-art work. Overall, we demonstrate the applicability of the speed-version Kyber implementation on memory-constrained IoT platforms and set new speed records for Kyber on these platforms.

Mobile smart devices provide convenience for people’s daily life with the users’ data, but also put consumers’ privacy and security at risk. Privacy-enhancing technologies (PETs), including secure two/multi-party computation, have emerged as solutions to alleviate privacy concerns in mobile cloud computing (MCC). However, cloud servers, although capable of easing the burden of PETs, introduce potential risks by being malicious and colluding with computation parties to access additional private data. In this article, we propose a privacy-preserving cloud-assisted two-party computation scheme and the optimized variant with the half-gate method in MCC with a higher security level. To the best of our knowledge, the work is the first cloud-assisted two-party computation, designed to resist all collusion attacks in the malicious model. This is achieved by distributing circuit generation tasks among the parties and separately processing private inputs based on authenticated garbled circuits. Security analysis demonstrates that our scheme ensures correctness and fairness. Performance comparison results indicate the efficiency of our work, even with stronger security against malicious servers and any collusion attack. It outperforms the state-of-the-art scheme, particularly in terms of the server’s communication cost in the online phase, achieving a remarkable reduction of approximately 96.8%.

The decentralized Federated Learning (FL) paradigm built upon blockchain architectures leverages distributed node clusters to replace the single server for executing FL model aggregation. This paradigm tackles the vulnerability of the centralized malicious server in vanilla FL and inherits the trustfulness and robustness offered by blockchain. However, existing blockchain-enabled schemes face challenges related to inadequate confidentiality on models and limited computational resources of blockchains. In this paper, we present Voltran, an innovative hybrid platform designed to achieve trust, confidentiality, and robustness for FL based on the combination of the Trusted Execution Environment (TEE) and blockchain technology. We offload the FL aggregation computation into TEE to provide an isolated, trusted and customizable off-chain execution and then guarantee the authenticity and verifiability of aggregation results on the blockchain. Moreover, we provide strong scalability on multiple FL scenarios by introducing a multi-SGX parallel execution strategy to amortize the large-scale FL workload. We implement a prototype of Voltran and conduct a comprehensive performance evaluation. Extensive experimental results demonstrate that Voltran incurs minimal additional overhead while guaranteeing trust, confidentiality, and authenticity, and it significantly brings a significant speed-up compared to state-of-the-art ciphertext aggregation schemes.

Prevailing smart devices collect individual or industrial sensitive data for collaborative computation to provide convenient service in heterogeneous networks. Nowadays, protecting privacy and security is a significant issue and raises increasing concerns in academia and industry. But diverse smart devices are equipped with unequal resources and some devices with limited resources cannot afford expensive privacy-preserving computation. In this article, we propose a generic efficient and privacy-preserving cloud-assisted two-party computation scheme for smart devices in heterogeneous networks. We adopt the cloud server to assist the collaborative computation and reduce the overhead of smart devices. Besides, we apply preprocessing and online phases to guarantee different devices to operate with a lower burden online. What is more, the work is, to our best knowledge, the first to resist the malicious cloud server and computing parties simultaneously by adopting authenticated masked bits to strengthen the garbled circuit scheme. At the same time, our scheme can guarantee correctness and fairness, as shown in security analysis. The performance comparison result shows that this work is efficient and surpasses the previous best counterpart scheme while maintaining nearly identical computation cost. It outperforms in terms of total communication cost by 49% and total execution time by 32%, even though it takes extra and acceptable cost in the online phase for stronger security against the malicious server.

Phishing scams are one of Ethereum's most representative security risks that can defraud many transactions in a short period and severely threaten network security. Existing deep learning-based phishing scam detection methods mainly rely on constructing static transaction graphs which are assumed to be accessible before model training. However, static methods that have a high false positive rate to detect newly generated phishing scams by adding this newly generated data to existing algorithms for execution, due to new accounts and transactions constantly appearing in the real-world Ethereum network. Therefore, this article, for the first time, proposes a novel evolve-based phishing scams detection method (named GrabPhisher) that extracts temporal features of accounts and captures information about the dynamic topology of the graph as it evolves. Specifically, GrabPhisher can build the evolutionary pattern of accounts trading on Ethereum as a diffusion network graph in continuous time. It can continue to capture new transaction features based on existing transactions, which facilitates the identification of phishing accounts. Additionally, we implement GrabPhisher on the real-world Ethereum phishing scams datasets. Extensive experimental results demonstrate that GrabPhisher can effectively extract dynamic temporal features and outperform state-of-the-art methods (95% Recall, and 88% F1-score).

In the past few years, numerous multi-view graph clustering algorithms have been proposed to enhance the clustering performance by exploring information from multiple views. Despite the superior performance, the high time and space expenditures limit their scalability. Accordingly, anchor graph learning has been introduced to alleviate the computational complexity. However, existing approaches can be further improved by the following considerations: (i) Existing anchor-based methods share the same number of anchors across views. This strategy violates the diversity and flexibility of multi-view data distribution. (ii) Searching for the optimal anchor number within hyper-parameters takes much extra tuning time, which makes existing methods impractical. (iii) How to flexibly fuse multi-view anchor graphs of diverse sizes has not been well explored in existing literature. To address the above issues, we propose a novel anchor-based method termed Flexible and Diverse Anchor Graph Fusion for Scalable Multi-view Clustering (FDAGF) in this paper. Instead of manually tuning optimal anchor with massive hyper-parameters, we propose to optimize the contribution weights of a group of pre-defined anchor numbers to avoid extra time expenditure among views. Most importantly, we propose a novel hybrid fusion strategy for multi-size anchor graphs with theoretical proof, which allows flexible and diverse anchor graph fusion. Then, an efficient linear optimization algorithm is proposed to solve the resultant problem. Comprehensive experimental results demonstrate the effectiveness and efficiency of our proposed framework. The source code is available at https://github.com/Jeaninezpp/FDAGF.

Multi-view clustering has gained broad attention owing to its capacity to exploit complementary information across multiple data views. Although existing methods demonstrate delightful clustering performance, most of them are of high time complexity and cannot handle large-scale data. Matrix factorization-based models are a representative of solving this problem. However, they assume that the views share a dimension-fixed consensus coefficient matrix and view-specific base matrices, limiting their representability. Moreover, a series of large-scale algorithms that bear one or more hyperparameters are impractical in real-world applications. To address the two issues, we propose an auto-weighted multi-view clustering (AWMVC) algorithm. Specifically, AWMVC first learns coefficient matrices from corresponding base matrices of different dimensions, then fuses them to obtain an optimal consensus matrix. By mapping original features into distinctive low-dimensional spaces, we can attain more comprehensive knowledge, thus obtaining better clustering results. Moreover, we design a six-step alternative optimization algorithm proven to be convergent theoretically. Also, AWMVC shows excellent performance on various benchmark datasets compared with existing ones. The code of AWMVC is publicly available at https://github.com/wanxinhang/AAAI-2023-AWMVC.

Improving the transferability of adversarial examples for the purpose of attacking unknown black-box models has been intensively studied. In particular, feature-level transfer-based attacks, which destroy the intermediate feature outputs of source models, are proven to generate more transferable adversarial examples. However, existing state-of-the-art feature-level attacks only destroy a single intermediate layer, this severely limits the transferability of adversarial examples. And all of these attacks have a vague distinction between positive and negative features. By contrast, we propose the Multi-layer Feature Division Attack (MFDA), which aggregates multi-layer feature information on the basis of feature division to attack. Extensive experimental evaluation demonstrates that MFDA can significantly boost the adversarial transferability and quantitatively distinguish the effects of positive and negative features on transferability. Compared to the state-of-the-art feature-level attacks, our improvement methods with MFDA increase the average success rate by 2.8% against normally trained models and 3.0% against adversarially trained models.

As an essential component part of the Intelligent Transportation System (ITS), the Internet of Vehicles (IoV) plays a vital role in alleviating traffic issues. Object detection is one of the key technologies in the IoV, which has been widely used to provide traffic management services by analyzing timely and sensitive vehicle-related information. However, the current object detection methods are mostly based on centralized deep training, that is, the sensitive data obtained by edge devices need to be uploaded to the server, which raises privacy concerns. To mitigate such privacy leakage, we first propose a federated learning-based framework, where well-trained local models are shared in the central server. However, since edge devices usually have limited computing power, plus a strict requirement of low latency in IoVs, we further propose a sparse training process on edge devices, which can effectively lighten the model, and ensure its training efficiency on edge devices, thereby reducing communication overheads. In addition, due to the diverse computing capabilities and dynamic environment, different sparsity rates are applied to edge devices. To further guarantee the performance, we propose, FedWeg, an improved aggregation scheme based on FedAvg, which is designed by the inverse ratio of sparsity rates. Experiments on the real-life dataset using YOLO show that the proposed scheme can achieve the required object detection rate while saving considerable communication costs.

In recent years, Ethereum has become a hotspot for criminal activities such as phishing scams that seriously compromise Ethereum transaction security. However, existing methods cannot accurately model Ethereum transaction data and make full use of the temporal structure information and basic account features. In this paper, we propose an Ethereum phishing detection framework based on temporal motif features. By designing a sampling method, we convert labeled Ethereum addresses into multi-directed transaction subgraphs with time and amount to avoid losing structure and attribute information. To learn representations for subgraphs, we define and extract the temporal motif features and general transaction features. Extensive experiments on Support Vector Machine, Random Forest, Logistic Regression, and XGBoost demonstrate that our method significantly outperforms all baselines and provides an effective phishing scams detection for Ethereum.

The technique of packing multiple values into one message without losing homomorphic computation properties is the main workhorse that drives many exciting advances in applying lattice-based homomorphic encryption schemes to privacy-preserving Machine-Learning-as-a-Service (MLaaS). However, this technique does not directly work for the classic Paillier homomorphic encryption scheme, limiting the use of the Paillier scheme in the privacy-preserving MLaaS. To enrich the applications of Paillier in privacy-preserving MLaaS, we present a set of new methods for efficient linear computations over packed values under the Paillier scheme, such as vector multiplication, matrix multiplication, and convolutional calculation between ciphertexts and plaintexts. Different from the packing methods of lattice-based schemes, the Paillier packing method naturally allows higher packing capability for values in lower bit-length. This property can significantly benefit privacy-preserving MLaaS, as the values of user inputs and parameters of machine learning models are often quantized into low bits (e.g., 1-8 bits). We conduct comparisons based on different linear computation tasks, the proposed methods under the Paillier scheme clearly outperform the state-of-the-art in terms of communication and computational efficiency, especially in realistic scenarios. For example, compared to one of the recent arts CrypTFlow2 [1], the communication cost of our solution can be 21.7× smaller at best. Thanks to the reduction of communication cost, the runtime can be 2.46× faster than CrypTFlow2 at the median-country-speed of current global mobile broadband.

Trajectory design is of great significance for the intelligent Unmanned Ground Vehicle (UGV) when performing various ground tasks. Though obstacle avoidance, speed control and other movement issues in the UGV navigation have been considered by the current research, the UGV path planning against malicious radio source is off the beaten path. To address such a research gap, we propose a reinforcement learning-based scheme to design UGV trajectory against malicious radio source as well as minimize the movement cost. Firstly, the malicious radio source detection and localization models are introduced after the Received Signal Strength Indicator (RSSI) map establishment. Then, the RSSI Map-based UGV trajectory design problem is formulated, where the movement cost and security risk are both concerned. To solve the formed problem, we propose a reinforcement learning-based trajectory design scheme, whose complexities are analyzed in detail. Finally, experiments are conducted under various parameter settings, where the simulation results evaluate the correctness and effectiveness of the proposed algorithm.

Internet of Things (IoT) is increasingly being used in real life, especially in the eHealthcare field. Among eHealthcare, the application of predicting patients' health status based on their daily activity data which is collected by IoT equipment has attracted extensive attentions and researches. In this application, patients' data which are treated as time-series data are transmitted to healthcare center (HC), then HC makes predictions based on an established classification model. However, making predictions using classification models requires a lot of computing resources, while HC usually cannot afford such numerous calculations. The use of the cloud solves the problem of insufficient computing resources, but it causes another problem, namely the leakage of user privacy. In particular, not only patients' data leak patients' privacy information, the classification model also causes the privacy disclosure of patients and HC. We design a new system model and propose an algorithm which can protect patients' data and classification model from leakage and offload calculation to multiple clouds. Our algorithm can better protect privacy of patients and HC in more complex classification scene, and can effectively reduce the computational cost of the healthcare center

Federated Learning (FL) is a framework where multiple parties can train a model jointly without sharing private data. Private information protection is a critical problem in FL. However, the communication overheads of existing solutions are too heavy for IoT devices in resource-constrained environments. Additionally, they cannot ensure robustness when IoT devices become offline. In this paper, Democratic Federated Learning (DemoFL) is proposed, which is a privacy-preserving FL framework that has sufficiently low communication overheads. DemoFL involves a consensus module to ensure the system is robust. It also utilizes a tree structure to reduce the time communication overheads and realizes high robustness without reducing accuracy. The proposed algorithm reduces the communication complexity of aggregation at training by M $M$ times, M $M$ being a controllable parameter. Sufficient experiments have been conducted to evaluate the efficiency of the proposed method. The experimental results also demonstrate the practicality of the proposed framework for IoT devices in unstable environments.

The timeless and efficient vehicle data transmission are the two common requirements for the Internet of Vehicles (IoV), especially the Unnamed Aircraft Vehicle (UAV)-aided Vehicular Edge Computing (VEC) network. Moreover, since the Age of Information (AoI) performance greatly influences these two indicators, data quality should be guaranteed in vehicle communication. However, few researchers pay attention to the AoI performance optimization issue regarding wireless resource constraint, transmission interference, and vehicle cooperation in recent years. To close this research gap, we propose an AoI-oriented channel access strategy in the UAV-aided VEC network from the game theory viewpoint. Firstly, the UAV-aided VEC network model and edge computing-based AoI expression are established and derived in the closed form, respectively. Subsequently, we transform the AoI minimization problem into an AoI-based channel access issue from the game theory viewpoint. Moreover, the stochastic learning-based algorithm is proposed to find the Nash Equilibrium (NE) solution of the formulated problem. Finally, simulation results evaluate the correctness and effectiveness of the proposed algorithms, where our scheme can achieve the better AoI value compared with baselines.

Narrowband-Internet of Things (NB-IoT) is an emerging cellular communication technology designed for low-power wide-area applications. Cell selection determines the channel of user device and hence is an important issue in cellular networks. In this article, we make the first attempt to examine and optimize the cell selection in NB-IoT networks by field measurement. We conduct measurements at 30 different locations which involve five typical application scenarios of NB-IoT. Two kinds of NB-IoT modules and two network operators are also involved in the measurements. We find four potential issues on the cell selection of the User Equipment (UE) through the measurements. We propose an adaptive cell selection approach to optimize the cell selection of UE. The simulation test based on real-world measurement data shows that the cell selected by the adaptive approach can improve the coverage level and reduce the power consumption for UE.

Scalable video coding (SVC) has received much attention for video transmission over wireless due to its flexibility. However, most previous work only considered SVC video streaming from a single base station (BS). At present, the densification of BSs enables a user equipment (UE) to connect to multiple BSs in ultra-dense networks (UDNs). In this paper, we consider the problem of SVC video streaming in a UDN, which allows different layers of a video block to be downloaded from different BSs. An optimization problem is formulated aiming to maximize the quality of experience (QoE) of users by selecting the optimal connection strategy and optimal number of video layers. Considering the complexity, to efficiently solve the problem in a distributed manner, the problem of choosing connection strategy is formulated as a multi-agent multi-armed bandit (MA-MAB) problem with only few information exchange. Each user can adapt its connection strategy in a distributed self-learning system. To obtain the optimal arm for the MA-MAB problem, we propose a multi-user arm decision algorithm. To avoid large computation and handover costs, we adopt the same connection strategy for the entire video sequence. Then for each video block, with the given connection strategy, the number of video layers is adjusted adaptively according to dynamic network conditions. Finally, based on the above designs, we provide the SVC-based video downloading scheme to obtain an approximate optimal solution to the original optimization problem. Extensive simulations and comparisons show the feasibility and superiority of the proposed scheme.

An unmanned aerial vehicle (UAV) network is an emerging industrial IoT network for collaborative UAV communication and management. The open architecture and dynamic topology, which provide functional benefits, unfortunately make UAVNs more vulnerable to a variety of attacks. In UAVNs, malicious nodes not only eavesdrop the communications between UAV nodes but also attempt to attack the entire network by injecting or modifying messages. This work proposes a provenance-aware distributed trust model, named UAV-pro, for UAVNs that aim to achieve accurate peer-to-peer trust assessment and maximize the delivery of correct messages received by destination nodes while minimizing the message delay and communication cost under resource-constrained network environments. Provenance refers to the history of ownership of messages transmitted on the network. The behavior of message creators and operators can be effectively evaluated based on message integrity, then generate the observational evidence. We collect the observational evidence for distributed trust evaluation, then identify malicious nodes in the network and isolate them from the network. UAVN-pro takes a data-driven approach to reduce resource consumption in the presence of selfish or malicious nodes while ensuring the safe transmission of data by digital signature technology. The experimental results show that UAVN-pro works are compatible with the existing UAV network routing protocols, and can effectively identify attacks, such as the black hole, gray hole, message modification, fake recommendation, and fake identity in UAV networks. UAVN-pro is superior to the existing security model in terms of detection rate, delivery rate, and system energy consumption in most cases.

Botmasters generate a large number of malicious algorithmically generated domains (mAGDs) through domain generation algorithms (DGAs) to infect a large number of hosts on a network, which creates inconvenience in people's network lives. The workload of detecting mAGDs by collecting the responses of the domain name system (DNS) is considerable. In this article, we propose a system named the automatic NXDomain classification system (ANCS) that can automatically identify and classify the nonexistent domain (NXD) as benign or malicious by studying the features extracted from benign NXDs (bNXDs) and mAGDs. The ANCS uses online, incremental, and fuzzy rough sets machine learning to improve the time, memory, false positive rate, false negative rate, and accuracy of the detection process. First, an online and incremental algorithm can reduce the training time. Second, the addition of fuzzy rough sets can dynamically adjust the degree of the membership function, optimizing the weight distribution of each feature, and further, improving the classification accuracy. The experimental evaluation shows that the ANCS can reach a very high classification accuracy at a low false positive rate and a low false negative rate, which has good practicability. Moreover, both time and memory are well guaranteed, and the ANCS also has good generalization performance, making up for sensitive points of noisy samples and the lack of nonincremental machine learning.

Apache Kafka, which is a high-throughput distributed message processing system, has been leveraged by the majority of enterprise for its outstanding performance. Unlike common cloud-based access control architectures, Kafka service providers often need to build their systems on other enterprises' high-performance cloud platforms. However, since the cloud platform belongs to a third party, it is not necessarily reliable. Paradoxically, it has been demonstrated that Kafka's data is stored in the cloud in the plaintext form, and thus poses a serious risk of user privacy leakage. In this paper, we propose a secure fine-grained data transmission scheme called Secure Door on Cloud (SDoC) to protect the data from being leaked in Kafka. SDoC is not only more secure than Kafka's built-in security mechanism, but also can effectively prevent third-party cloud from stealing plaintext data. To evaluate the performance of the SDoC, we simulate normal inter-entity communication and show that Kafka with SDoC integration has a lower data transfer time overhead than that of Kafka with built-in security mechanism opened.

Over the years, public health has faced a large number of challenges like COVID-19. Medical cloud computing is a promising method since it can make healthcare costs lower. The computation of health data is outsourced to the cloud server. If the encrypted medical data is not decrypted, it is difficult to search for those data. Many researchers have worked on searchable encryption schemes that allow executing searches on encrypted data. However, many existing works support single-keyword search. In this article, we propose a patient-centered fine-grained attribute-based encryption scheme with multi-keyword search (CP-ABEMKS) for medical cloud computing. First, we leverage the ciphertext-policy attribute-based technique to construct trapdoors. Then, we give a security analysis. Besides, we provide a performance evaluation, and the experiments demonstrate the efficiency and practicality of the proposed CP-ABEMKS.

Privacy-preserving data aggregation is a kind of fundamental and essential algorithm for wireless sensor networks. However, the existing aggregation algorithms consume a large amount of energy to assure sensory data security. In this article, we propose an energy-efficient and privacy-preserving data aggregation algorithm (EPDA). We organize a sensor network into a tree and connect the leaf nodes of the tree to form many chains. EPDA requires only the data sensed by the tail nodes of the chains to be sliced to ensure privacy. Also, EPDA significantly decreases energy consumption and prolongs the lifetime of the network. We compare our scheme with the existing schemes through theoretical analysis and simulations. The analysis and simulation results show that EPDA outperforms the existing schemes.

Elliptic Curve Cryptography (ECC) now is one of the most important approach to instantiate asymmetric encryption and signature schemes, which has been extensively exploited to protect the security of cyber-physical systems. With the advent of the Internet of Things (IoT), a great deal of constrained devices may require software implementations of ECC operations. Under this circumstances, the SM2, a set of public key cryptographic algorithms based on elliptic curves published by Chinese Commercial Cryptography Administration Office, was standardized at ISO in 2017 to enhance the cyber-security. However, few research works on the implementation of SM2 for constrained devices have been conducted. In this work, we fill this gap and propose our efficient, secure, and compact implementation of scalar multiplication on a 256-bit elliptic curve recommended by the SM2, as well as a comparison implementation of scalar multiplication on the same bit-length elliptic curve recommended by NIST. We re-design some existent techniques to fit the low-end IoT platform, namely 8-bit AVR processors, and our implementations evaluated on the desired platform show that the SM2 algorithms have competitive efficiency and security with NIST, which would work well to secure the IoT world.

The universality of smart-devices has brought rapid development and the significant advancement of ubiquitous applications for the Internet of Things (IoT). Designing new types of IoT-compatible cryptographic protocols has become a more popular way to secure IoT-based applications. Significant attention has been dedicated to the challenge of implementing a lightweight and secure cryptographic protocol for IoT devices. In this study, we propose a lightweight cryptographic protocol integrating certificateless signature and bilinear pairing crypto-primitives. In the proposed protocol, we elegantly refine the processes to account for computation-limited IoT devices during security operations. Rigorous security analyses are conducted to guarantee the robustness of the proposed cryptographic protocol. In addition, we demonstrate a thorough performance evaluation, where an IoT-based test-bed, i.e., the Raspberry PI, is simulated as the underlying platform of the implementation of our proposed cryptographic protocol. The results show the practicability of the proposed protocol.

Lightweight Elliptic Curve Cryptography (ECC) is a critical component for constructing the security system of Internet of Things (IoT). In this paper, we define an emerging family of lightweight elliptic curves to meet the requirements on some resource-constrained devices. We present the design of a scalable, regular, and highly-optimized ECC library for both MICAz and Tmote Sky nodes, which supports both widely-used key exchange and signature schemes. Our parameterized implementation of elliptic curve group arithmetic supports pseudo-Mersenne prime fields at different security levels with two optimized-specific designs: the high-speed version (HS) and the memory-efficient (ME) version. The former design achieves record times for computation of cryptographic schemes at roughly$80\sim 128$-bit security levels, while the latter implementation only requires half of the code size of the current best implementation. We also describe our efforts to evaluate the energy consumption and harden our library against some basic side-channel attacks, e.g., timing attacks and simple power analysis (SPA) attacks.