Crowdsensing Systems Research Articles

L3P-DLI: A Lightweight Positioning-Privacy Protection Scheme With Double-Layer Incentives for Wireless Crowd Sensing Systems

L3P-DLI: A Lightweight Positioning-Privacy Protection Scheme With Double-Layer Incentives for Wireless Crowd Sensing Systems

Truth discovery for mobile workers in edge-assisted mobile crowdsensing

The proliferation of mobile phones has led to the rise of mobile crowdsensing systems. However, many of these systems rely on the deep cloud, which can be complex and challenging to scale. To improve the performance of crowdsensing at the edge cloud, truth-discovery methods are commonly employed. These methods typically involve updating either the truth or the weight associated with a user’s task. While some edge cloud-based crowdsensing systems exist, they do not provide incentives to users based on their experience. In this report, we present a new approach to truth discovery and incentive-giving that considers both the user’s experience and the accuracy of their submitted data. Our modified truth-discovery algorithm updates both the weight and truth concurrently, with greater incentives offered to users who have completed more tasks and whose submitted data is close to the estimated truth. We have run simulations to show how well our suggested strategy works to enhance the incentive system for experienced users.

FedCrow: Federated-Learning-Based Data Privacy Preservation in Crowd Sensing

In the process of completing large-scale and fine-grained sensing tasks for the new generation of crowd-sensing systems, the role of analysis, reasoning, and decision making based on artificial intelligence has become indispensable. Mobile crowd sensing, which is an open system reliant on the broad participation of mobile intelligent terminal devices in data sensing and computation, poses a significant risk of user privacy data leakage. To mitigate the data security threats that arise from malicious users in federated learning and the constraints of end devices in crowd-sensing applications, which are unsuitable for high computational overheads associated with traditional cryptographic security mechanisms, we propose FedCrow, which is a federated-learning-based approach for protecting crowd-sensing data that integrates federated learning with crowd sensing. FedCrow enables the training of artificial intelligence models on multiple user devices without the need to upload user data to a central server, thus mitigating the risk of crowd-sensing user data leakage. To address security vulnerabilities in the model data during the interaction process in federated learning, the system employs encryption methods suitable for crowd-sensing applications to ensure secure data transmission during the training process, thereby establishing a secure federated-learning framework for protecting crowd-sensing data. To combat potential malicious users in federated learning, a legitimate user identification method based on the user contribution level was designed using the gradient similarity principle. By filtering out malicious users, the system reduces the threat of attacks, thereby enhancing the system accuracy and security. Through various attack experiments, the system’s ability to defend against malicious user attacks was validated. The experimental results demonstrate the method’s effectiveness in countering common attacks in federated learning. Additionally, through comparative experiments, suitable encryption methods based on the size of the data in crowd-sensing applications were identified to effectively protect the data security during transmission.

An Adaptive Temporal Convolutional Network Autoencoder for Malicious Data Detection in Mobile Crowd Sensing.

Mobile crowdsensing (MCS) systems rely on the collective contribution of sensor data from numerous mobile devices carried by participants. However, the open and participatory nature of MCS renders these systems vulnerable to adversarial attacks or data poisoning attempts where threat actors can inject malicious data into the system. There is a need for a detection system that mitigates malicious sensor data to maintain the integrity and reliability of the collected information. This paper addresses this issue by proposing an adaptive and robust model for detecting malicious data in MCS scenarios involving sensor data from mobile devices. The proposed model incorporates an adaptive learning mechanism that enables the TCN-based model to continually evolve and adapt to new patterns, enhancing its capability to detect novel malicious data as threats evolve. We also present a comprehensive evaluation of the proposed model's performance using the SherLock datasets, demonstrating its effectiveness in accurately detecting malicious sensor data and mitigating potential threats to the integrity of MCS systems. Comparative analysis with existing models highlights the performance of the proposed TCN-based model in terms of detection accuracy, with an accuracy score of 98%. Through these contributions, the paper aims to advance the state of the art in ensuring the trustworthiness and security of MCS systems, paving the way for the development of more reliable and robust crowdsensing applications.

Multisource Sparse Inversion Localization with Long-Distance Mobile Sensors

To address the threat posed by unknown signal sources within Mobile Crowd Sensing (MCS) systems to system stability and to realize effective localization of unknown sources in long-distance scenarios, this paper proposes a unilateral branch ratio decision algorithm (UBRD). This approach addresses the inadequacies of traditional sparse localization algorithms in long-distance positioning by introducing a time–frequency domain composite block sparse localization model. Given the complexity of localizing unknown sources, a unilateral branch ratio decision scheme is devised. This scheme derives decision thresholds through the statistical characteristics of branch residual ratios, enabling adaptive control over iterative processes and facilitating multisource localization under conditions of remote blind sparsity. Simulation results indicate that the proposed model and algorithm, compared to classic sparse localization schemes, are more suitable for long-distance localization scenarios, demonstrating robust performance in complex situations like blind sparsity, thereby offering broader scenario adaptability.

Blockchain-Based Lightweight and Privacy-Preserving Quality Assurance Framework in Crowdsensing Systems

The novel sensing paradigm known as crowdsensing leverages ubiquitous smart devices to collect data in Internet of Things (IoT) applications. Traditional crowdsensing schemes assume a central framework to execute truth discovery algorithm to assure data quality, which may introduce reliability and privacy issues. Blockchain is a promising technology that provides a decentralized, transparent, and immutable platform. However, designing a blockchain-based quality assurance scheme in crowdsensing is not a trivial problem. First, truth discovery is a time-consuming iterative algorithm, which is not practical to execute on blockchain. Second, privacy-preserving schemes always require that the participants join in multi-round communications, which is not acceptable in open blockchain because of users’ highly unpredictable behaviors. Finally, on-chain data are publicly accessible, and achieving a good balance between data utility and privacy is an important issue. In this paper, we propose a lightweight quality assurance framework atop blockchain to build a reliable, privacy-preserving, and fair crowdsensing system. Specifically, we carefully design two kinds of smart contracts to cooperatively maintain a long-term reliable platform to execute crowdsensing tasks. In the contracts, we devise a reputation-based aggregator selection algorithm to reach the consensus on truthful results while avoiding expensive on-chain iterative processes. The participant selection scheme and reward policy are further utilized to filter appropriate participants to complete the task. Our scheme also protects data privacy and does not require communications between participants. Finally, we implement and deploy the contracts on Ethereum and conduct extensive experiments to demonstrate that the contracts can practically execute crowdsensing tasks.

UAV-Assisted Mobile Crowdsensing Systems Empowered by Wireless Power Transfer and Adaptive Compression Techniques

UAV-Assisted Mobile Crowdsensing Systems Empowered by Wireless Power Transfer and Adaptive Compression Techniques

Computation offloading in blockchain-enabled MCS systems: A scalable deep reinforcement learning approach

In Mobile Crowdsensing (MCS) systems, cloud service providers (CSPs) pay for and analyze the sensing data collected by mobile devices (MDs) to enhance the Quality-of-Service (QoS). Therefore, it is necessary to guarantee security when CSPs and users conduct transactions. Blockchain can secure transactions between two parties by using the Proof-of-Work (PoW) to confirm transactions and add new blocks to the chain. Nevertheless, the complex PoW seriously hinders applying Blockchain into MCS since MDs are equipped with limited resources. To address these challenges, we first design a new consortium blockchain framework for MCS, aiming to assure high reliability in complex environments, where a novel Credit-based Proof-of-Work (C-PoW) algorithm is developed to relieve the complexity of PoW while keeping the reliability of blockchain. Next, we propose a new scalable Deep Reinforcement learning based Computation Offloading (DRCO) method to handle the computation-intensive tasks of C-PoW. By combining Proximal Policy Optimization (PPO) and Differentiable Neural Computer (DNC), the DRCO can efficiently make the optimal/near-optimal offloading decisions for C-PoW tasks in blockchain-enabled MCS systems. Extensive experiments demonstrate that the DRCO reaches a lower total cost (weighted sum of latency and power consumption) than state-of-the-art methods under various scenarios.

A method of user recruitment and adaptation degree improvement via community collaboration in sparse mobile crowdsensing systems

The task allocation problem in sparse mobile crowdsensing is simplified as a subarea selection problem. However, the lack of participants in some high-value subareas leads to the low quality of the final inferred sensing map. To solve this problem, a method of user recruitment and adaptation degree improvement via community collaboration is proposed. Firstly, the adjacency matrix is constructed based on the social relationship of the participants, and then all the participants are classified into communities by the non-negative matrix factorization method of deep autoencoder-like; secondly, the perception platform matches the perception tasks with the centroids of the perception communities based on the different eigenvalues of the classified perception communities and the location characteristics of the perception tasks. After the matching is completed, some participants in the matched communities will be selected to complete the perceptual tasks under the constraint of perceptual cost; finally, the perceptual data provided by the participants is used to obtain the complete perceptual map using the compressed perceptual algorithm. We designed this user recruitment method to obtain high-quality sensing data by recruiting a small number of users after community classification based on their social relationships and then accurately inferring the entire perceptual map. The experimental results based on the Gowalla and U-Air datasets show that the user recruitment method proposed in this paper can infer accurate data with fewer sensing areas, which is significantly better than other comparison methods.

Budget-feasible Sybil-proof mechanisms for crowdsensing

The rapid use of smartphones and devices leads to the development of crowdsensing (CS) systems where a large crowd of participants can take part in performing data collecting tasks in large-scale distributed networks. Participants/users in such systems are usually selfish and have private information, such as costs and identities. Budget-feasible mechanism design, as a sub-field of auction theory, is a useful paradigm for crowdsensing, which naturally formulates the procurement scenario with buyers' budgets being considered and allows the users to bid their private costs. Although the bidding behavior is well-regulated, budget-feasible mechanisms are still vulnerable to the Sybil attack where users may generate multiple fake identities to manipulate the system. Thus, it is vital to provide Sybil-proof budget-feasible mechanisms for crowdsensing. In this paper, we design a budget-feasible incentive mechanism which can guarantee truthfulness and deter Sybil attack. We prove that the proposed mechanism achieves individual rationality, truthfulness, budget feasibility, and Sybil-proofness. Extensive simulation results further validate the efficiency of the proposed mechanism.

Collision-free parking recommendation based on multi-agent reinforcement learning in vehicular crowdsensing

The recent proliferation of Fifth-Generation (5G) networks and Sixth-Generation (6G) networks has given rise to Vehicular Crowd Sensing (VCS) systems which solve parking collisions by effectively incentivizing vehicle participation. However, instead of being an isolated module, the incentive mechanism usually interacts with other modules. Based on this, we capture this synergy and propose a Collision-free Parking Recommendation (CPR), a novel VCS system framework that integrates an incentive mechanism, a non-cooperative VCS game, and a multi-agent reinforcement learning algorithm, to derive an optimal parking strategy in real time. Specifically, we utilize an LSTM method to predict parking areas roughly for recommendations accurately. Its incentive mechanism is designed to motivate vehicle participation by considering dynamically priced parking tasks and social network effects. In order to cope with stochastic parking collisions, its non-cooperative VCS game further analyzes the uncertain interactions between vehicles in parking decision-making. Then its multi-agent reinforcement learning algorithm models the VCS campaign as a multi-agent Markov decision process that not only derives the optimal collision-free parking strategy for each vehicle independently, but also proves that the optimal parking strategy for each vehicle is Pareto-optimal. Finally, numerical results demonstrate that CPR can accomplish parking tasks at a 99.7% accuracy compared with other baselines, efficiently recommending parking spaces.

Joint privacy and data quality aware reward in opportunistic Mobile Crowdsensing systems

Mobile Crowdsensing (MCS) is a paradigm involving a crowd of participants, called workers, into sensor data gathering campaigns through their personal devices. Some campaigns require workers to contribute with small amounts of geolocalized data at a constant rate, while being not directly aware of the global conditions of the system. In the scope of this reduced awareness, it is crucial to consider the privacy preservation of single workers at design time, as the disclosure of their exact location may lead to severe privacy issues. In this paper we design a privacy by design MCS framework that leverages variable rewards for workers willing to submit their location with an higher precision than others. Privacy is ensured through a negotiation phase that estimates the reward of the workers for different levels of location precision. This way, it helps them decide autonomously the spatial granularity of their data in order to preserve their privacy, yet obtaining a reward for their data. We design a metric based on k-anonymity to evaluate the level of privacy achieved, and validate the proposed framework over a real dataset. Our results show the efficacy of the framework as well as interesting effects caused by the topology of the environment.

Q-Learning-Based Hyperheuristic Evolutionary Algorithm for Dynamic Task Allocation of Crowdsensing.

Task allocation is a crucial issue of mobile crowdsensing. The existing crowdsensing systems normally select the optimal participants giving no consideration to the sudden departure of mobile users, which significantly affects the sensing quality of tasks with a long sensing period. Furthermore, the ability of a mobile user to collect high-precision data is commonly treated as the same for different types of tasks, causing the unqualified data for some tasks provided by a competitive user. To address the issue, a dynamic task allocation model of crowdsensing is constructed by considering mobile user availability and tasks changing over time. Moreover, a novel indicator for comprehensively evaluating the sensing ability of mobile users collecting high-quality data for different types of tasks at the target area is proposed. A new Q -learning-based hyperheuristic evolutionary algorithm is suggested to deal with the problem in a self-learning way. Specifically, a memory-based initialization strategy is developed to seed a promising population by reusing participants who are capable of completing a particular task with high quality in the historical optima. In addition, taking both sensing ability and cost of a mobile user into account, a novel comprehensive strength-based neighborhood search is introduced as a low-level heuristic (LLH) to select a substitute for a costly participant. Finally, based on a new definition of the state, a Q -learning-based high-level strategy is designed to find a suitable LLH for each state. Empirical results of 30 static and 20 dynamic experiments expose that this hyperheuristic achieves superior performance compared to other state-of-the-art algorithms.

Group effect-based privacy-preserving data aggregation for mobile crowdsensing

In mobile crowdsensing systems, the public crowd are required to report data with actual locations under location privacy vulnerabilities. Moreover, even sensing data itself further deepens location privacy breaches. Existing works allow each worker to consider his own privacy, but the accumulated privacy budget will lower down group data privacy of each sensing region. Moreover, multi-region spatial data correlations indicate that multi-group correlated data privacy may be leaked from each other. To this end, we develop a novel MCS framework, called GDA-Crowd(Group effect-based Data Aggregation), which consists of three parts: location obfuscation and aggregation, group effect-based data privacy and aggregation, and incentive mechanism. We start from individual location privacy guarantee and propose a location aggregation method to cluster workers into groups. Then, we exploit intra-group effect, i.e., data privacy interdependence under the judicious selection of workers’ participation, to enhance privacy-accuracy balance. Moreover, multi-group global histogram incorporates inter-group effect, i.e., correlated privacy loss from spatial data correlations, into inter-group data aggregation. Finally, we design a truthful, individually rational and computationally efficient incentive mechanism for participant selection. The synopsis of contributions includes dual privacy protection, dual group effect for desirable privacy-accuracy tradeoff, synergies among incentive mechanism, privacy-preserving data aggregation for approximate optimality. Theoretical analysis and extensive experiments validate our effectiveness and superiority.

Teletraffic analysis of a mobile crowdsensing system: The pedestrian-to-vehicle scenario

Crowdsensing systems are developed in order to use the computational and communication capabilities of registered users to monitor specific variables and phenomena in an opportunistic manner. As such, the Quality of Experience is not easily attained since these systems heavily rely on the user’s behavior and willingness to cooperate whenever an event with certain interest needs to be monitored. In this work, we analyze the data acquisition phase, where pedestrians opportunistically transmit to vehicles to further disseminate it in the city according to their trajectory. This highly dynamic environment (sensors and data sinks are mobile, and the number of users varies according to the region and time) poses many challenges for properly operating a crowdsensing system. We first study the statistical properties of vehicular traffic in different regions of Luxembourg City where pedestrians share their computational resources and send data to passing cars. Then we propose an Erlang distribution to model the vehicles’ dwelling times and develop a Markov chain accordingly. We model the system using two different queues: we use a single server queue to model the vehicle traffic, while we use an infinite server queue system to model the pedestrian traffic.

Blockchain-Enabled Conditional Decentralized Vehicular Crowdsensing System

The rapid growth of connected and autonomous vehicles (CAVs) shows an urgent demand for driving and transportation-related data, which gives rise to vehicular crowdsensing systems (VCSs). Nevertheless, the existing centralized VCS framework mainly faces the system reliability problem while the decentralized one cannot satisfy the management flexibility. In addition, when the privacy preservation scheme that prevents information leakage encounters the user selection scheme that desires detailed information of participants, how to balance this seemingly irreconcilable contradiction is inevitable for VCS. To remedy that, we take the first research attempt and explore the balance point between the system management, privacy preservation, and quality of experience (QoE) of participants. By fully exploiting the characters of participating entities, a blockchain-enabled conditional decentralized VCS is proposed in this paper. Firstly, we propose a privacy-preserving scheme where the zk-SNARK proof combines with the mixed-task smart contract to guarantee the interaction process will not reveal any private information of participants. Secondly, we propose an efficient reputation management mechanism that renders certain the participants can get a satisfactory QoE even under the condition that the private information of users is secured. And also, the malicious operations in the system will be effectively supervised. Theoretical analysis and extensive simulations demonstrate the security and efficiency properties of privacy preservation and indicate the effectiveness of reputation management.

A Truthful Double Auction Mechanism for Multi-Resource Allocation in Crowd Sensing Systems

As a novel sensing paradigm, crowd sensing systems have gained great attention and been widely adopted in the environmental monitoring and calculation areas. In crowd sensing systems, mobile users provide their multiple resources to the requesters to execute tasks. Existing studies focus on the divisible task or one-to-one mapping for single resource allocation. However, this assumption does not hold for crowd sensing systems. Owing to the task attribute, some tasks cannot be divided into multiple parts to run on different devices. In addition, a high performance mobile device can execute multiple tasks simultaneously. We address the problem of multi-resource allocation in crowd sensing systems for the auction-based model considering many-to-one mapping for indivisible tasks, where many-to-one mapping allows one mobile device to provide multiple resources to execute one or more tasks. In this article, we study, for the first time to the best of our knowledge, a truthful mechanism that stimulates mobile users and requesters to declare their true values. We design a truthful double auction mechanism together with a payment scheme tailored to fit it that would help researchers understand how a truthful double auction mechanism can be designed. In addition, we prove that our proposed mechanism maintains budget-balance, individual rationality, and computational tractability. Furthermore, we analyze the approximation ratio of our proposed approximation algorithm. Experimental results demonstrate that our proposed mechanism has high computation efficiency and good performance.

Towards a privacy-preserving smart contract-based data aggregation and quality-driven incentive mechanism for mobile crowdsensing

The crowd's power, combined with the sensing capabilities of smart mobile de-vices, has resulted in the emergence of a revolutionary data acquisition paradigm known as Mobile Crowdsensing. In exchange for rewards, mobile users collect and share location-specific data values. However, most existing crowdsensing systems built on traditional centralized architectures are highly prone to attacks, intrusions, single point of failure, manipulations, and low reliability. Recently, decentralized blockchain technologies are being applied in mobile crowdsensing systems to ensure workers' privacy, data privacy, and the quality of sensed data at a low service fee. By leveraging blockchain technology, this paper inherits the advantages of the public blockchain without the need for any trusted third-parties. We propose a smart contract-based privacy-preserving data aggregation and quality assessment protocol to infer reliable aggregated results and estimate data quality, wherein, we design a fair quality-driven incentive mechanism to distribute rewards based on the data quality. The protocol ensures a secure, cost-optimal, and reliable aggregation and estimation of the sensed data quality on the public blockchain without disclosing the sensed data's and participants' privacy. We adopt Interplanetary File Systems to offset the blockchain's expensive storage costs. Experiments were conducted using real-world datasets which were implemented on a full-stack on-chain and off-chain decentralized application on the Ethereum blockchain. The experimental results demonstrate our design is highly efficient in achieving privacy-preserving data aggregation and significantly reduces on-chain computation costs.

CrowdHB: A Decentralized Location Privacy-Preserving Crowdsensing System Based on a Hybrid Blockchain Network

With the advent of the Internet of Things (IoT), crowdsensing, as a new emerging application of the IoT that employs ubiquitous mobile users with smartphones for data collection and processing, has further deepened our knowledge. However, the problems of the current crowdsensing systems regarding system security, user privacy, and user payment (UP) raise serious privacy and security concerns, which affect participants’ adoption of the system. The Blockchain technology allows for nondeterministic multiple parties to interact with each other anonymously in a network that is not fully trusted. In this article, we propose a new decentralized crowdsensing system, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CrowdHB</i> . Unlike other blockchain-based crowdsensing systems, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CrowdHB</i> adopts a hybrid blockchain architecture and uses smart contracts to achieve location privacy preservation and ensure data quality while improving the system performance. Furthermore, to optimize task assignments to mobile users, we propose a location privacy-preserving optimization mechanism (LPPOM) and the approach of consistency optimization (ACO) to achieve a tradeoff between user privacy and system performance. The extensive experimental results show that the proposed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CrowdHB</i> outperforms the other crowdsensing systems in terms of task success rate and performance for a large number of mobile users and tasks.

Distributed Visual Crowdsensing Framework for Area Coverage in Resource Constrained Environments.

Visual crowdsensing applications using built-in cameras in smartphones have recently attracted researchers’ interest. Making the most out of the limited resources to acquire the most helpful images from the public is a challenge in disaster recovery applications. Proposed solutions should adequately address several constraints, including limited bandwidth, limited energy resources, and interrupted communication links with the command center or server. Furthermore, data redundancy is considered one of the main challenges in visual crowdsensing. In distributed visual crowdsensing systems, photo sharing duplicates and expands the amount of data stored on each sensor node. As a result, if any node can communicate with the server, then more photos of the target region would be available to the server. Methods for recognizing and removing redundant data provide a range of benefits, including decreased transmission costs and energy consumption overall. To handle the interrupted communication with the server and the restricted resources of the sensor nodes, this paper proposes a distributed visual crowdsensing system for full-view area coverage. The target area is divided into virtual sub-regions, each of which is represented by a set of boundary points of interest. Then, based on the criteria for full-view area coverage, a specific data structure theme is developed to represent each photo with a set of features. The geometric context parameters of each photo are utilized to extract the features of each photo based on the full-view area coverage criteria. Finally, data redundancy removal algorithms are implemented based on the proposed clustering scheme to eliminate duplicate photos. As a result, each sensor node may filter redundant photographs in dispersed contexts without requiring high computational complexity, resources, or global awareness of all photos from all sensor nodes inside the target area. Compared to the most recent state-of-the-art, the improvement ratio of the added values of the photos provided by the proposed method is more than 38%. In terms of traffic transfer, the proposed method requires fewer data to be transferred between sensor nodes and between sensor nodes and the command center. The overall reduction in traffic exceeds 20% and the overall savings in energy consumption is more than 25%. It was evident that in the proposed system, sending photos between sensor nodes, as well as between sensor nodes and the command center, consumes less energy than existing approaches due to the considerable amount of photo exchange required. Thus, the proposed technique effectively transfers only the most valuable photos needed.