Large language models (LLMs) have transformed code generation.However, most existing approaches focus on mainstream languages such as Python and Java, neglecting the Solidity language, the predominant programming language for Ethereum smart contracts.Due to the lack of adequate benchmarks for Solidity, LLMs' ability to generate secure, costeffective smart contracts remains unexplored.To fill this gap, we construct SolEval, the first repository-level benchmark designed for Solidity smart contract generation, to evaluate the performance of LLMs on Solidity.Sol-Eval consists of 1,507 samples from 28 different repositories, covering 6 popular domains, providing LLMs with a comprehensive evaluation benchmark.Unlike the existing Solidity benchmark, SolEval not only includes complex function calls but also reflects the real-world complexity of the Ethereum ecosystem by incorporating Gas@k and [email protected] evaluate 16 LLMs on SolEval, and our results show that the best-performing LLM achieves only 26.29% Pass@10, highlighting substantial room for improvement in Solidity code generation by LLMs.Additionally, we conduct supervised fine-tuning (SFT) on Qwen-7B using SolEval, resulting in a significant performance improvement, with Pass@5 increasing from 16.67% to 58.33%, demonstrating the effectiveness of fine-tuning LLMs on our benchmark.We release our data and code at https: //github.com/pzy2000/SolEval.

Domain generalization (DG) strives to address distribution shifts across diverse environments to enhance model’s generalizability. Current DG approaches are confined to acquiring robust representations with continuous features, specifically training at the pixel level. However, this DG paradigm may struggle to mitigate distribution gaps in dealing with a large space of continuous features, rendering it susceptible to pixel details that exhibit spurious correlations or noise. In this paper, we first theoretically demonstrate that the domain gaps in continuous representation learning can be reduced by the discretization process. Based on this inspiring finding, we introduce a novel learning paradigm for DG, termed Discrete Domain Generalization (DDG). DDG proposes to use a codebook to quantize the feature map into discrete codewords, aligning semantic-equivalent information in a shared discrete representation space that prioritizes semantic-level information over pixel-level intricacies. By learning at the semantic level, DDG diminishes the number of latent features, optimizing the utilization of the representation space and alleviating the risks associated with the wide-ranging space of continuous features. Extensive experiments across widely employed benchmarks in DG demonstrate DDG’s superior performance compared to state-of-the-art approaches, underscoring its potential to reduce the distribution gaps and enhance the model’s generalizability.

While Large Language Models (LLMs) have demonstrated remarkable progress in generating functionally correct Solidity code, they continue to face critical challenges in producing gas-efficient and secure code, which are critical requirements for real-world smart contract deployment. Although recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) for code preference alignment, existing approaches treat functional correctness, gas optimization, and security as independent objectives, resulting in contracts that may achieve operational soundness but suffer from prohibitive execution costs or dangerous vulnerabilities. To address these limitations, we propose PrefGen, a novel framework that extends standard DPO beyond human preferences to incorporate quantifiable blockchain-specific metrics, enabling holistic multi-objective optimization specifically tailored for smart contract generation. Our framework introduces a comprehensive evaluation methodology with four complementary metrics: Pass@k (functional correctness), Compile@k (syntactic correctness), Gas@k (gas efficiency), and Secure@k (security assessment), providing rigorous multi-dimensional contract evaluation. Through extensive experimentation, we demonstrate that PrefGen significantly outperforms existing approaches across all critical dimensions, achieving 66.7% Pass@5, 58.9% Gas@5, and 62.5% Secure@5, while generating production-ready smart contracts that are functionally correct, cost-efficient, and secure.

Existing federated learning frameworks are primarily designed for single-modal data. However, real-world scenarios require processing multi-modal data on heterogeneous devices. The gap between existing methods and real-world scenarios presents challenges in processing multimodal data on heterogeneous devices, significantly impacting model training efficiency. To address these issues, we propose a multimodal federated learning framework, which integrates multimodal algorithms with a semi-synchronous training method. The multimodal algorithm trains local autoencoders on different data modalities. By leveraging the similarity of encodings across different modalities with the same data labels, we further train and aggregate these local autoencoders into a global autoencoder, which is then deployed on the blockchain to perform downstream classification tasks. In the semi-synchronous training method, each device updates its parameters independently during a round. At the end of each round, a global aggregation combines the updates from devices. We conduct an empirical evaluation of our framework on various multimodal datasets, including Opportunity (Opp) Challenge, mHealth, and UR Fall Detection datasets. Experimental results demonstrate that our federated learning framework, outperforms the state-of-the-art multimodal frameworks on three multimodal datasets, achieving an average accuracy improvement of 9.07%. Furthermore, in terms of training speed, MMFed is obviously superior to synchronization strategies when it is extended to a large number of clients.

With the development of quantum blockchain, the quantum consensus protocols have garnered increasing attention, which play a crucial role in driving the implementation of quantum blockchains. However, existing protocols, derived from the classical consensus algorithms, face practical application challenges due to current quantum technology limitations. The first challenge is the bottleneck in generating large-scale entangled quantum states. The second challenge arises from the generation of malicious quantum states. The final challenge involves privacy concerns. To address these challenges, we propose a practical iterative QUantum consensus protocol with sharding construction, namely, Q-Union. In fact, Q-Union employs an iterative consensus algorithm where participating nodes are divided into multiple smaller shards, with the consensus process occurring within the current shard, and new shards are involved only if consensus is not achieved. Leveraging Greenberger-Horne- Zeilinge states and Aharonov states, Q-Union harnesses the advantages of quantum mechanics to achieve anonymous consensus, protecting the private information of participating nodes. Additionally, by integrating state verification, Q-Union ensures the correctness of the consensus procedure in the presence of malicious nodes generating adversarial quantum states. Finally, it is proven that Q-Union can also defend against Byzantine attacks from adversarial nodes, maintaining the same security level as traditional non-sharded consensus protocols. Specifically, it consistently outputs the correct consensus when the fraction of adversaries among participating nodes is less than 1/2 with synchronous communication. Both the theoretical analysis and performance illustration demonstrate the superior performance of the proposed Q-Union compared to state-of-the-art protocols.

In recent years, there has been growing interest in heterogeneous distributed storage systems (DSSs), such as clustered DSSs, which are widely used in practice. However, research regarding information-theoretic security in heterogeneous DSSs remains limited. Furthermore, unlike traditional DSSs, the heterogeneous DSSs face eavesdropper with diverse operating patterns, complicating the secrecy models. In this paper, we aim to investigate the secrecy capacity and code constructions for clustered DSSs (CDSSs), a type of heterogeneous DSSs in which the system is divided into clusters with an equal number of nodes and different repair bandwidths for intra-cluster and cross-cluster against two types of eavesdroppers: the occupying-type eavesdropper and the osmotic-type eavesdropper. We construct two CDSS secrecy models tailored to these aforementioned eavesdroppers, derive the upper bounds on adjustable secrecy capacities, and explore the relationships between the upper bounds of perfect secrecy capacities and the number of compromised nodes. Notably, the upper bounds obtained in this paper generalize those of the traditional DSS model. Additionally, we propose three repair-by-transfer code constructions that achieve the secrecy capacity under both eavesdropper scenarios. These codes are based on nested MDS code and represent a generalized form of the minimum bandwidth regenerating (MBR) codes in traditional DSSs.

Generalization under distribution shifts has been a great challenge in computer vision. The prevailing practice of directly employing the one-hot labels as the training targets in domain generalization (DG) can lead to gradient conflicts, making it insufficient for capturing the intrinsic class characteristics and hard to increase the intra-class variation. Besides, existing methods in DG mostly overlook the distinct contributions of source (seen) domains, resulting in uneven learning from these domains. To address these issues, we first present a theoretical and empirical analysis on the existence of gradient conflicts in DG, unveiling the previously unexplored relationship between distribution shifts and gradient conflicts during optimization process. In this paper, we present a novel perspective of DG from the empirical source domain's risk, and propose a new paradigm for DG called Diverse Target and Contribution Scheduling (DTCS). DTCS comprises two innovative modules: Diverse Target Supervision (DTS) and Diverse Contribution Balance (DCB), with the aim of addressing the limitations associated with the common utilization of one-hot labels and equal contributions for source domains in DG. In specific, DTS employs distinct soft labels as training targets to account for various feature distributions across domains and thereby mitigates the gradient conflicts, and DCB dynamically balances the contributions of source domains by ensuring a fair decline in losses of different source domains. Extensive experiments with analysis on four benchmark datasets show that the proposed method achieves a competitive performance in comparison with the state-of-the-art approaches, demonstrating the effectiveness and advantages of the proposed DTCS. The source code will be available at https://github.com/longshaocong/DTCS.

In mobile crowd sensing systems, existing flight control methods enable unmanned aerial vehicles (UAVs) to provide high-quality data collection services for various applications. However, due to limited communication range, UAVs typically collect data under partial observability, hindering optimal performance without global environmental information. Additionally, many methods fail to enforce critical safety constraints. This paper proposes a communication-assisted safe multi-agent actor-critic-based UAV flight control method (CSMAAC). First, we propose an independent prediction communication partner model to address the partial observability problem. Based on the UAV's local observation, causal inference is used to obtain prior communication information between UAVs through a feed-forward neural network to help UAVs determine potential communication partners. Second, we utilize a critic-network to predict and quantify inter-UAV influence and determine the necessity of communication. By exchanging necessary information inter-UAV, UAVs can perceive global information, thereby solving the UAV's partial observability problem and reducing communication overhead. Moreover, we propose a similarity enhancement mechanism to improve the learning efficiency of the model by enhancing the connection between UAV observations and the policies of other UAVs. Finally, we introduce a safety layer to Actor-Network to ensure safe UAV flight. The simulation results show that the proposed method outperforms the baselines.

Harnessing the benefits of blockchain, such as decentralization, immutability, and transparency, to bolster the credibility and security attributes of federated learning (FL) has garnered increasing attention. However, blockchain-enabled FL (BFL) still faces several challenges. The primary and most significant issue arises from its essential but slow validation procedure, which selects high-quality local models by recruiting distributed validators. The second issue stems from its incentive mechanism under the transparent nature of blockchain, increasing the risk of privacy breaches regarding workers’ cost information. The final challenge involves data eavesdropping from shared local models. To address these significant obstacles, this paper proposes a Blockchain-enabled Incentivized and Secure Federated Learning (BIT-FL) framework. BIT-FL leverages a novel loop-based sharded consensus algorithm to accelerate the validation procedure, ensuring the same security as non-sharded consensus protocols. It consistently outputs the correct local model selection when the fraction of adversaries among validators is less than$1/2$with synchronous communication. Furthermore, BIT-FL integrates a randomized incentive procedure, attracting more participants while guaranteeing the privacy of their cost information through meticulous worker selection probability design. Finally, by adding artificial Gaussian noise to local models, it ensures the privacy of trainers’ local models. With the careful design of Gaussian noise, the excess empirical risk of BIT-FL is upper-bounded by$\mathcal {O}(\frac{\ln n_{\min}}{ n_{\min}^{3/2}}+\frac{\ln n}{n})$, where$n$represents the size of the union dataset, and$n_{{\min}}$represents the size of the smallest dataset. Our extensive experiments demonstrate that BIT-FL exhibits efficiency, robustness, and high accuracy for both classification and regression tasks.

In this paper, we investigate a resource orchestration and transmission scheduling problem for data-intensive services with diversified service requirements. A three-layer collaborative architecture is presented to support dynamic networking and computing resource allocation. To obtain optimal orchestration and scheduling policies, we formulate a constrained resource scheduling problem with the objective to maximizing resource utilization and scheduling success ratio. Since the complicated coupled constraints among decisions, we decouple the problem into a two-stage sub-problems of resource orchestration and transmission scheduling. To realize cross-domain resource orchestration and deterministic transmission of large-scale computing tasks, a two-stage resource scheduling scheme is proposed. Specifically, the first stage makes the resource orchestration decision by a greedy algorithm, and the second stage makes the transmission scheduling decision based on a deep reinforcement learning algorithm. Simulation results show that the proposed solution can effectively improve resource utilization and scheduling success ratio while satisfying diversified service requirements, as compared with benchmarks.

With the rising proliferation of blockchain systems and applications, choosing the appropriate blockchains to deploy applications is critical to achieving optimal performance. Evaluation frameworks provide a systematic approach to assessing and comparing different blockchain systems, guiding application developers to choose the most suitable one. However, existing evaluation frameworks still have limitations that affect their accuracy. First, most frameworks utilize workloads initially de-signed for traditional databases, which fail to capture the unique characteristics and requirements of blockchain systems. Second, these frameworks fail to generate correct results under heavy workloads due to their imbalanced task processing algorithms. Third, existing frameworks are tailored only for non-sharding blockchain architectures, limiting their ability to evaluate diverse blockchains. This paper introduces Hammer, a general blockchain evaluation framework that addresses the above limitations. It consists of two key components: workload prediction and asynchronous task processing. Workload prediction accurately predicts real-world workload trends by expanding the scope of temporal control sequences, providing a more realistic evaluation of blockchain performance. Asynchronous task processing handles heavy-load situations, enabling accurate evaluation of blockchain performance. Extensive experiments on various blockchains under Smallbank workload empower application developers to make informed decisions about blockchain selection and optimization.

Due to the progress in computer hardware and network technologies, federated learning (FL), a decentralized training method in machine learning, has garnered widespread attention. In this approach, individuals share local model parameters rather than raw training data to protect their privacy. However, the inherent heterogeneity of practical computing devices poses challenges to the efficiency and performance of FL. In this paper, we explore the landscape of heterogeneous FL frameworks and introduce ChronusFed, a reinforCement-based adaptive partial training method for heterogeneous Federated learning. ChronusFed employs a dynamic epoch adjustment mechanism (DEA) and a customizable partial training framework (CPT) to optimize model training efficiency. By integrating DEA and CPT, ChronusFed effectively tackles the straggler issues that arise from limited hardware resources, while simultaneously enhancing the model performance. More specifically, DEA leverages deep reinforcement learning (DRL) to model the current state of the global model and determine optimal local training epochs, while CPT utilizes our proposed maximum coverage algorithm to handle device heterogeneity and accelerate model convergence. Theoretical analysis of training convergence validates the effectiveness of ChronusFed, and comprehensive experimental evaluations demonstrate that ChronusFed outperforms state-of-the-art methods across various learning tasks, showcasing its robustness and superiority in heterogeneous FL scenarios.

Erasure codes are widely implemented in distributed storage systems to provide high fault tolerance with small storage overhead. Maximum distance separable codes are an common choice as they achieve the optimal tradeoff between fault tolerance and storage overhead. In this paper, we focus on the repair of multiple erasures of binary MDS array codes. Specifically, we present constructions of binary MDS array codes with optimal cooperative repair bandwidth by stacking multiple Blaum-Roth code instances whose “evaluation points” are judiciously designed. The constructed array codes with length$n$and dimension$k$can achieve the optimal cooperative repair bandwidth for$2\leq h\leq n-k$and$k+1\leq d\leq n-h$where$h$and$d$are the numbers of failed nodes and helper nodes, respectively. As the codes are constructed on a special polynomial ring over binary field, computation operations involved in nodes repair and file reconstruction for these codes are only XORs and cyclic shifts. Moreover, due to the inherent parallel structure of the codes, both the encoding and decoding procedures can be finished in parallel, speeding up the computing process.

Domain generalization (DG) aims at solving distribution shift problems in various scenes. Existing approaches are based on Convolution Neural Networks (CNNs) or Vision Transformers (ViTs), which suffer from limited receptive fields or quadratic complexity issues. Mamba, as an emerging state space model (SSM), possesses superior linear complexity and global receptive fields. Despite this, it can hardly be applied to DG to address distribution shifts, due to the hidden state issues and inappropriate scan mechanisms. In this paper, we propose a novel framework for DG, named DGMamba, that excels in strong generalizability toward unseen domains and meanwhile has the advantages of global receptive fields, and efficient linear complexity. Our DGMamba compromises two core components: Hidden State Suppressing (HSS) and Semantic-aware Patch Refining (SPR). In particular, HSS is introduced to mitigate the influence of hidden states associated with domain-specific features during output prediction. SPR strives to encourage the model to concentrate more on objects rather than context, consisting of two designs: Prior-Free Scanning (PFS), and Domain Context Interchange (DCI). Concretely, PFS aims to shuffle the non-semantic patches within images, creating more flexible and effective sequences from images, and DCI is designed to regularize Mamba with the combination of mismatched non-semantic and semantic information by fusing patches among domains. Extensive experiments on four commonly used DG benchmarks demonstrate that the proposed DGMamba achieves remarkably superior results to state-of-the-art models. The code will be made publicly available at https://github.com/longshaocong/DGMamba.

Nowadays, unmanned aerial vehicles (UAVs) are widely applied in crowd sensing. For UAV-enabled crowd sensing (UAVCS) systems, the sensing outcome and charging cost are two primary concerns. To achieve a satisfactory sensing outcome under the charging budget, we exploit joint moving, sensing, and charging scheduling of UAVs, as they all have critical impacts on such two objectives. However, the dynamically generated sensing targets and the variety of sensing tasks a UAVCS system may face make farsighted scheduling of UAVs rather challenging. To this end, we propose a novel multi-task constrained multi-agent reinforcement learning (MARL) method to help UAVs make distributed moving, sensing, and charging decisions. Specifically, we design a multi-task MARL framework to learn a single generic policy for a large collection of tasks, and propose a primal-dual training algorithm that alternates between improving the overall sensing outcome and reducing each task's constraint violation. Theoretically, we show that our algorithm provably converges, and analyze the optimality gap and constraint violation of the trained policy on unseen tasks. Extensive experiments on an incident dataset in New York City demonstrate that our method outperforms strong baselines in sensing outcome maximization and budget satisfaction, and also generalize well to unseen tasks.

Federated learning (FL) is an innovative distributed privacy-preserving machine learning paradigm, which enables participants to collaboratively train artificial intelligence (AI) models without disclosing private data. Nevertheless, malicious participants have the potential to introduce vicious models via poisoning attacks, which jeopardizes the convergence and accuracy of the global model in FL. In this article, we propose a secure FL distributed architecture based on deep deterministic policy gradient (DDPG), which advances the accuracy of the global model and enhances system robustness. Specifically, we model the accuracy optimization problem with the goal of minimizing the overall loss function of participating devices during each FL iteration. Furthermore, we design the device nodes selection mechanism, named FedSAP, which leverages social attribute perception. Particularly, we first construct the device node selection problem as a Markov decision process (MDP), and then apply social attribute perception and attribute information to the state space ensuring the reliability of the device. Moreover, the long short term memory (LSTM) algorithm is introduced into the actor-critic network structure to learn part of the hidden state through memory inference. The extensive experimental results show that FedSAP can effectively select reliable nodes and significantly improve the accuracy of the global model.

Domain generalization (DG) endeavours to develop robust models that possess strong generalizability while preserving excellent discriminability. Nonetheless, pivotal DG techniques tend to improve the feature generalizability by learning domain-invariant representations, inadvertently overlooking the feature discriminability. On the one hand, the simultaneous attainment of generalizability and discriminability of features presents a complex challenge, often entailing inherent contradictions. This challenge becomes particularly pronounced when domain-invariant features manifest reduced discriminability owing to the inclusion of unstable factors,i.e., spurious correlations. On the other hand, prevailing domain-invariant methods can be categorized as category-level alignment, susceptible to discarding indispensable features possessing substantial generalizability and narrowing intra-class variations. To surmount these obstacles, we rethink DG from a new perspective that concurrently imbues features with formidable discriminability and robust generalizability, and present a novel framework, namely, Discriminative Microscopic Distribution Alignment (DMDA). DMDA incorporates two core components: Selective Channel Pruning (SCP) and Micro-level Distribution Alignment (MDA). Concretely, SCP attempts to curtail redundancy within neural networks, prioritizing stable attributes conducive to accurate classification. This approach alleviates the adverse effect of spurious domain-invariance and amplifies the feature discriminability. Besides, MDA accentuates micro-level alignment within each class, going beyond mere category-level alignment. This strategy accommodates sufficient generalizable features and facilitates within-class variations. Extensive experiments on four benchmark datasets corroborate that DMDA achieves comparable results to state-of-the-art methods in DG, underscoring the efficacy of our method. The source code will be available at https://github.com/longshaocong/DMDA.

Mobile crowd sensing (MCS) has emerged as an increasingly popular sensing paradigm due to its cost-effectiveness. This approach relies on platforms to outsource tasks to participating workers when prompted by task publishers. Although incentive mechanisms have been devised to foster widespread participation in MCS, most of them focus only on static tasks (i.e., tasks for which the timing and type are known in advance) and do not protect the privacy of worker bids. In a dynamic and resource-constrained environment, tasks are often uncertain (i.e., the platform lacks a priori knowledge about the tasks) and worker bids may be vulnerable to inference attacks. This paper presents an incentive mechanism HERALD*, that takes into account the uncertainty and hidden bids of tasks without real-time constraints. Theoretical analysis reveals that HERALD* satisfies a range of critical criteria, including truthfulness, individual rationality, differential privacy, low computational complexity, and low social cost. These properties are then corroborated through a series of evaluations.

Maximum distance separable codes are commonly used in large-scale distributed storage systems since they achieve the maximum fault tolerance for some given redundancy. In this paper, we focus on the repair problem of MDS codes. By stacking multiple Blaum-Roth code instances of which the parity-check matrices are judiciously designed, we construct three families of binary MDS array codes with optimal repair bandwidth for single-node failure. Specifically, codes in the first family achieve the lower bound on repair bandwidth where the number of helper nodes d is n − 1; The second family of codes are optimal-repair for any fixed d and the third are for multiple values of d simultaneously. Moreover, the last two also possess error-resilient capability and can achieve the corresponding optimal repair bandwidth. All the codes in this paper are constructed on a particular polynomial ring over binary field. Consequently, computation operations involved in node repair and file reconstruction for these codes are only XORs and cyclic shifts, avoiding complex multiplications and divisions over large finite fields.

As smart devices are becoming increasingly common in people’s daily lives, privacy and security concerns make data collection expensive and limited, which further hinder the development of data-driven tasks. This paper studies how to better conduct private data trading via a novel generator method rather than direct trading of raw data. This new method facilitates more convenient data transactions by generator, protects the privacy of data owners and is satisfactory in terms of privacy compensation and query pricing. In detail, we propose RARIEA, a market framework for tRading privAte data geneRators based on GAN under rényI diffErential privAcy, which involves data owners, a data broker, and data consumers. To start, the broker employs the GAN training generator to augment the data to relieve the data shortage, introducing noise into its training process to preserve the owners’ privacy. After that, the broker uses rényi differential privacy to quantify the privacy loss at the data item level during the GAN training process and compensates each owner according to their respective privacy policies. Finally, the data broker charges each of the data consumers for their queries, where the price is lower bounded by the total privacy compensation. We then evaluate the performance of RARIEA on classic data sets: MNIST, Fashion-MNIST, and CelebA. The analysis and simulation results reveal that the generator provided by RARIEA can not only meet the data consumers’ demand for quantity and quality but also protect the owners’ privacy. In addition, RARIEA not only allows finer control over data owner compensation, but also excels at controlling the data broker’s revenue to improve market efficiency while ensuring fairness, balance, and monotonicity of pricing.

The strong secrecy transmission problem of the arbitrarily varying wiretap channel (AVWC) with input and state constraints is investigated in this paper. First, a stochastic-encoder code lower bound of the strong secrecy capacity is established by applying the type argument and Csiszár’s almost independent coloring lemma. Then, a superposition stochastic-encoder code lower bound of the secrecy capacity is provided. The superposition stochastic-encoder code lower bound can be larger than the ordinary stochastic-encoder code lower bound. Random code lower and upper bounds of the secrecy capacity of the AVWC with constraints are further provided. Based on these results, we further consider a special case of the model, namely severely less noisy AVWC, and give the stochastic-encoder code and random code capacities. It is proved that the stochastic-encoder code capacity of the AVWC with constraints is either equal to or strictly smaller than the corresponding random code capacity, which is consistent with the property of the ordinary AVC. Finally, some numerical examples are presented to better illustrate our capacity results. Compared to the soft covering lemma that requires the codewords to be generated i.i.d., our method has more relaxed requirements regarding codebooks. It is proved that the good codebooks for secure transmission can be generated by choosing codewords randomly from a given type set, which is critical when considering the AVWC with constraints.

The strong secrecy transmission problem of arbitrarily varying wiretap channel (AVWC) with input and state constraints is investigated in this paper. A stochastic code lower bound of the secrecy capacity is established by applying the type argument and Csiszár's almost independent coloring lemma, which includes the result of the ordinary AVWC as special case. Our codebook generation without the i.i.d. assumption of the soft covering lemma is to ensure the reliable communication over the AVWC with constraints. It is proved that the 0good codebooks for the strong secrecy transmission can be generated by choosing codewords randomly from a given type set, which is critical in this model.

In recent years, crowdsensing has received extensive attention both in academia and industry. However, most of the prior works are based on centralized framework, where the users upload the sensor data to a platform alone. In this paper, we propose a decentralized data aggregation algorithm for crowdsensing, in which, participants negotiate the average of their sensor data in a pure distributed manner while enjoying differential privacy guarantee. Taking participants' privacy into consideration, we first redesign a distributed averaging algorithm by artificially adding random noise to accommodate the mobile crowdsensing scenario, where the sensor data may be sensible. We prove that, though random noises are involved, our algorithm almost surely yields an unbiased estimate of the exact average. We further theoretically formulate the trade-offs between differential privacy and the accuracy of the algorithm. Finally, we give the optimal choice for the additive noise with respect to the variance minimization of the estimate. The extensive simulations and realword test demonstrate the effectiveness of our algorithm.

Mobile crowdsening (MCS) recently has been regarded as a newly-emerged sensing paradigm, which consists of a centralized cloud-based platform, some data demanders and some workers. However, since the platform needs to process tons of sensory data which is requested by the demanders and submitted by a large number of workers, this traditional MCS system may cause a heavy latency and serious network congestion, and thus can not be employed to some real-time and large-scale applications. Therefore, a new MCS system has been proposed recently by combining the edge computing, where some edge nodes (e.g., the base stations, laptops, smartphones) are added between the platform and workers to offload some operations from the platform to the network edges. Similar to the traditional MCS system, since participating in such edge-assisted MCS system is costly, it is important to attract more participation. However, this is more difficult since the platform and workers do not have direct communications with each other, which makes the edge nodes arbitrarily manipulate the information they transfer. Therefore, unlike the prior arts, we propose a novel incentive mechanism, namely, CHASTE, for such edge-assisted MCS system consisting of multiple demanders, some edge nodes and a crowd of workers where all of them behave strategically to maximize their own utility. Specifically, CHASTE is able to stimulate the participation, and satisfies the three-party truthfulness, three-party individual rationality, budget balance, as well as high social welfare. The desirable properties of CHASTE are validated through both theoretical analysis and extensive simulations.

Exploiting the computing capability of mobile devices with specialized engines (e.g., Neural Engine in iPhone), an attractive paradigm of federated learning that combines the mobile crowdsensing (MCS) has been deeply investigated recently (e.g., Google AI and Nvidia), where the training task is offloaded to the mobile crowd. However, this new paradigm still has numerous problems. Since executing the training task is costly for individual workers, the first problem is how to attract more participants. Following the incentive requirement, the second is how to preserve the workers' bid privacy since the reported costs are usually sensitive. Finally, the third problem is to guarantee the privacy protection on locally training models in the federated learning which involve the private information of local data. In this paper, we propose an incentivized federated learning with differential privacy in MCS system, namely, SHIELD, to solve the three significant problems. In fact, SHIELD satisfies the truthfulness and individual rationality while preserving the differential privacy of workers' bids and locally training models. Furthermore, for accuracy, the excess empirical risk of 1 SHIELD is proved to be upper bounded by O((ln(Knmin))1/2/Knmin+ ln(Knmin)/K2nmin2), where a special case for totally distributed scenario leads to a much sharper bound O( log(n)/n2) than the latest result O(ln(mnmin)/m2nmin2). Finally, comparing with the state-of-art apmin proaches, SHIELD illustrates superior performance by numerous experiments in classification and regression tasks.