27 February 2024 in IEEE Transactions on Network Science and Engineering
Empowered by crowdsensing technology, unmanned aerial vehicles (UAVs) equipped with rich sensors can perform sensing tasks in extreme scenarios. However, due to the selfishness and distrust of UAVs, some malicious UAVs with insufficient resources may provide false sensing data to the task publishers. In addition, the centralized sensing platform is vulnerable to various attacks (e.g., data tampering attacks and single point of failure) in traditional crowdsensing, resulting in degraded data quality and severe security issues. To cope with these problems, we propose a blockchain-based crowdsensing framework with reputation incentive (BCFR) for UAV-assisted mobile crowdsensing. Specifically, a reputation-based incentive scheme is first proposed to relate the behavior of each UAV with its reputation, and then to choose UAVs with high reputation to perform sensing tasks, thereby improving the security of sensing data sharing. Afterwards, we design a blockchain-based secure data transmission scheme to securely record data transactions of UAVs. Furthermore, UAVs may be reluctant to perform compute-intensive mining tasks due to their limited computing capabilities. Therefore, a two-stage Stackelberg game is introduced to motivate UAVs to participate in the block creation process. In a more realistic scenario, where participants are bounded rational, prospect theory (PT) is utilized to capture the potential subject perceptions of UAVs. Finally, simulation results and security analysis demonstrate that the proposed BCFR scheme can effectively improve the probability of successful mining and ensure the security of data sharing.
19 February 2024 in IEEE Transactions on Mobile Computing
Unmanned Aerial Vehicles (UAVs) have attracted extensive attention from both industry and academia owing to their high mobility, line-of-sight (LoS) characteristics of air-to-ground (A2G) channels, and low cost. However, the broadcast nature of wireless transmission and the LoS characteristics of A2G channels are vulnerable to eavesdropping attacks, which leads to severe security issues. To enhance the security of UAV communication, we propose a framework that multiple UAVs cooperate to resist attacks (MURA). Specifically, we first introduce an efficient incentive scheme based on the coalition game to motivate UAVs to participate in a coalition. By forming a grand coalition, we demonstrate that each individual UAV can maximize its utility. Additionally, we propose a secure UAV communication scheme designed to counter eavesdropping attacks. Two distinct types of scenarios are considered in UAV communication. In a completely rational scenario, in which participants make decisions aiming to maximize their utility, we utilize the Stackelberg game to model the interactions between UAVs and attacker. The existence and uniqueness of the equilibrium solution are proved, and the equilibrium solution is obtained. In the context of an imperfectly rational scenario, we employ the prospect theory (PT) to effectively capture the underlying rationality exhibited by the players. The PT valuations of the players, i.e., UAV and attacker, are deduced in detail. Meanwhile, the convergence of the PT valuations of UAV and attacker is proved. Finally, extensive simulation results show that the proposed scheme can effectively improve the utility of legal UAVs and ensure the security of the UAV networks compared with benchmarks.
23 October 2024 in IEEE Transactions on Information Forensics and Security
The integration of unmanned aerial vehicles (UAVs) and artificial intelligence (AI) has garnered significant interest as a promising paradigm for facilitating intelligent and pervasive mobile crowdsensing (MCS) services. In traditional AI methodologies, the centralization of large volumes of privacy-sensitive sensory data shared by UAVs for model training entails substantial privacy risks. Federated learning (FL) emerges as an appealing privacy-preserving paradigm that enables participating UAVs to collaboratively train shared models while safeguarding the privacy of their data. However, given that the execution of FL tasks inherently requires the consumption of resources such as power and bandwidth, rational and self-interested UAVs may not actively engage in FL or launch free-riding attacks (i.e., sharing fake local models) to mitigate costs. To address the above challenges, we propose a truthful incentive scheme in FL-based UAV-assisted MCS. Specifically, we first present a learning framework tailored for realistic scenarios in UAV-assisted MCS that enhances privacy preservation and optimizes communication efficiency during AI model training for collaborative UAVs, where the sensing platform (i.e., the aggregation server) is the finite-rational decision maker. Then, based on prospect theory (PT), we design an incentive mechanism to motivate UAVs to participate in FL. In this mechanism, a PT-based game is exploited to model the interactions between the sensing platform and UAVs, where the equilibrium is derived. Moreover, we employ a zero-payment mechanism to curb the self-interested behavior of UAVs. Finally, simulation results show that the proposed scheme can facilitate high-quality model sharing while suppressing free-riding attacks.
13 September 2021 in IEEE Internet of Things Journal
At present, the crowdsourcing-based indoor navigation system (CINS) has attracted extensive attention from both industry and academia owing to its low-cost and high-accuracy performance. Unfortunately, the system that relies on crowdsourced data is vulnerable to the collusion attack, which leads to severe security issues. To address the security issues in the CINS, we propose to utilize a fully trusted fog server platform to advocate secure transactions between service requesters and responders. First, we propose a novel reputation incentive mechanism based on the behaviors of responders. Then, we employ the offensive and defensive game to model the interactions between the fog server platform and the responders, whereby a social welfare optimization problem is formulated to maximize the social welfare of the system. Next, the game equilibriums are found by using the replicator dynamic equation while the game stability is discussed. Finally, the simulation results show that the proposed mechanism can effectively encourage responders to provide positive navigation services and obtain more social welfare of the system compared with the conventional mechanisms.
6 August 2024 in IEEE Transactions on Network and Service Management
Unmanned aerial vehicles (UAVs) combined with tagging applications (Apps) have recently attracted considerable attention to enable efficient mobile crowdsensing (MCS) applications in scenarios where an insufficient number of UAVs may be available to perform the sensing tasks. However, there remain potential security and incentive threats for App-and UAV-assisted crowdsensing owing to the presence of malicious UAVs and the selfishness of UAVs. To address these issues, we propose a two-stage secure incentive mechanism in the App-and UAV-assisted MCS. Specifically, we first develop an App-and UAV-assisted MCS framework, where the App tags the location of the sensing task as a point-of-interest (PoI) to attract registered UAVs, thus assisting the platform to complete the sensing task efficiently. To motivate the App to cooperate with the sensing platform, we design a double auction-based incentive mechanism for PoI-tagging tasks in the first stage, where the optimal price for PoI-tagging services is obtained by applying a double auction game. Furthermore, we evaluate each UAV through comprehensive consideration of the performance and security of UAVs for most task-suitable UAV recruitment and malicious UAVs prevention. Additionally, in the second stage, based on the Stackelberg game theory, an incentive mechanism for sensing tasks is proposed to encourage UAV participation. Finally, simulation results and security analysis validate the proposed mechanism can greatly increase the utility of UAVs and the App while ensuring the security of the sensing process.
16 July 2025 in IEEE Transactions on Dependable and Secure Computing
The convergence of unmanned aerial vehicles (UAVs) and federated learning (FL) has emerged as a promising paradigm to facilitate artificial intelligence (AI) services with enhanced privacy preservation. However, notwithstanding the inherent advantages of FL in terms of privacy protection, attackers can still exploit inference attacks to deduce raw data of UAVs. The existing studies predominantly assume FL servers to be fully rational and have access to all privacy preference information of UAVs (i.e., information symmetry scenario), in the design of privacy-preserving incentive schemes. To tackle these challenges, we propose a privacy-preserving incentive scheme for UAV-aided FL in the presence of information asymmetry while considering FL servers exhibit bounded rationality. Specifically, a practical UAV-aided FL framework is first introduced to enable AI model training between UAVs and the FL server with bounded rationality. In addition, based on differential privacy, we quantify the privacy level of UAVs and subsequently analyze its impact on the aggregation accuracy of the server. This scenario entails two conflicting objectives: the server aims for higher-quality local models to achieve better aggregation accuracy, while UAVs prioritize injecting more noise into their local models to enhance privacy protection. To reconcile the conflicting objectives, we develop an incentive mechanism based on contract theory to optimize the server's aggregation accuracy in the presence of information asymmetry. Furthermore, we employ prospect theory (PT) to the above contract to capture biases in the server's subjective decision-making process. Besides, we deduce closedform solutions for optimal contracts under PT and expected utility theory (EUT), where participants are assumed to be fully rational. Finally, simulation results validate the superiority of our proposed scheme in motivating UAVs to share high-quality local models and improving the aggregation accuracy of the server.