Space-air-ground integrated networks can provide better connectivity and improved performance to ground users and thus have been well-recognized as the innovative trend for future 6G and beyond wireless systems. However, such heterogeneous and complex integrated communication systems also pose many new challenges for joint performance optimization. In this paper, we study the data delivery optimization problem in a space-air-ground network, where joint resource management decisions on user association, bandwidth allocation, cache placement, and high-altitude platform (HAP) location selection have to be optimized. To tackle this complex and challenging mixed integer programming optimization problem, we introduce a quantum-assisted method, named the Hybrid quantum-classical Benders’ Decomposition (HyBD) algorithm, which leverages the strengths of both quantum and classical computing. Experiments on the commercial quantum annealing machine demonstrate the effectiveness and robustness of the proposed HyBD method, with up to 64.3% improvement of iteration number and 82.8% improvement of average computation time over the classical Benders’ Decomposition algorithm on classical CPUs even at small scales, which demonstrates the quantum advantage.

In the era of 6G and beyond, space-aerial-terrestrial quantum networks (SATQNs) are poised to advance the development of a global-scale quantum Internet. These networks leverage free space optical satellite and aerial quantum networks to complement optical fiber-based terrestrial quantum networks to enable the distribution of high-fidelity quantum entanglement over long distances. However, establishing multi-hop end-to-end quantum entanglement remains highly challenging, not only due to time-varying link conditions and structural heterogeneity inherent in SATQNs, but also because noise in quantum channels and imperfections in quantum operations can degrade the quality of entanglement. To address this challenge, we formulate an optimization problem that maximizes SATQN throughput by jointly optimizing routing path selection and entanglement generation rates (PS-EGR) while ensuring high entanglement fidelity. The resulting problem is a mixed-integer linear programming (MILP) formulation, which is NP-hard. We propose a Benders’ decomposition (BD)-based approach to solve this problem efficiently. Specifically, the MILP is decomposed into a master problem for binary routing path selection and a subproblem for continuous entanglement generation rate optimization. Numerical results validate the effectiveness of the proposed PS-EGR scheme, offering critical insights into the optimization and deployment of SATQNs.

Federated learning (FL) over mobile devices is an emerging distributed learning paradigm for numerous delay sensitive applications. In FL, the training delay is composed of the computing and communication delay. Some of the participating mobile devices may have slow local computing or wireless communications, which results in high FL training delay. Intuitively, if fast devices help slow ones, the FL training delay can potentially be reduced. However, helping each other among devices requires frequent transmissions and may cause additional delay. Fortunately, we observe that device-to-device (D2D) transmission, a fast and direct transmission, may be applied between device pairs to mitigate the additional delay from frequent transmissions. Inspired by those observations, we develop the D2D transmission assisted FL (DAFL), a novel FL scheme to improve the training delay over mobile devices. Briefly, we first put the eligible mobile devices into pairs, assigning each pair to one of the four types of relation: 1) similar computing, large communication gap; 2) similar communication, large computing gap; 3) one with faster computing and the other with faster communication; and 4) one with both faster computing and communication. We design the process for each type of device pair to: 1) improve the transmission delay of each pair, by letting the fast device help with the model parameters transmission to the server and 2) improve the computing delay by splitting learning task between paired devices. The emulation results demonstrate that DAFL surpasses existing peer designs in terms of reducing training delay by more than 20%.

Network function virtualization (NFV)-enabled space information network (SIN) has emerged as a promising method to facilitate global coverage and seamless service. This paper proposes a novel NFV-enabled SIN to provide end-to-end communication and computation services for ground users. Based on the multi-functional time expanded graph (MF-TEG), we jointly optimize the user association, virtual network function (VNF) deployment, and flow routing strategy (U-VNF-R) to maximize the total processed data received by users. The original problem is a mixed-integer linear program (MILP) that is intractable for classical computers. Inspired by quantum computing techniques, we propose a hybrid quantum-classical Benders’ decomposition (HQCBD) algorithm. Specifically, we convert the master problem of the Benders’ decomposition into the quadratic unconstrained binary optimization (QUBO) model and solve it with quantum computers. To further accelerate the optimization, we also design a multi-cut strategy based on the quantum advantages in parallel computing. Numerical results demonstrate the effectiveness and efficiency of the proposed algorithm and U-VNF-R scheme.

In the era of Internet of Things (IoT), multi-access edge computing (MEC)-enabled satellite-aerial-terrestrial integrated network (SATIN) has emerged as a promising technology to provide massive IoT devices with seamless and reliable communication and computation services. This paper investigates the cooperation of low Earth orbit (LEO) satellites, high altitude platforms (HAPs), and terrestrial base stations (BSs) to provide relaying and computation services for vastly distributed IoT devices. Considering the uncertainty in dynamic SATIN systems, we formulate a stochastic optimization problem to minimize the time-average expected service delay by jointly optimizing resource allocation and task offloading while satisfying the energy constraints. To solve the formulated problem, we first develop a Lyapunov-based online control algorithm to decompose it into multiple one-slot problems. Since each one-slot problem is a large-scale mixed-integer nonlinear program (MINLP) that is intractable for classical computers, we further propose novel hybrid quantum-classical generalized Benders’ decomposition (HQCGBD) algorithms to solve the problem efficiently by leveraging quantum advantages in parallel computing. Numerical results validate the effectiveness of the proposed MEC-enabled SATIN schemes.

Motivated by the drawbacks of cloud-based federated learning (FL), cooperative federated edge learning (CFEL) has been proposed to improve efficiency for FL over mobile edge networks, where multiple edge servers collaboratively coordinate the distributed model training across a large number of edge devices. However, CFEL faces critical challenges arising from dynamic and heterogeneous device properties, which slow down the convergence and increase resource consumption. This paper proposes a heterogeneity-aware CFEL scheme calledHeterogeneity-Aware Cooperative Edge-based Federated Averaging(HCEF) that aims to maximize the model accuracy while minimizing the training time and energy consumption via adaptive computation and communication compression in CFEL. By theoretically analyzing how local update frequency and gradient compression affect the convergence error bound in CFEL, we develop an efficient online control algorithm for HCEF to dynamically determine local update frequencies and compression ratios for heterogeneous devices. Experimental results show that compared with prior schemes, the proposed HCEF scheme can maintain higher model accuracy while reducing training latency and improving energy efficiency simultaneously.

Accurate and timely building damage assessments are crucial for effective disaster response. However, traditional damage assessment methods heavily rely on manual evaluations by experts, which are labor-intensive and time-consuming. Recent research leverages machine learning (ML) and satellite remote sensing techniques to streamline the process. A major challenge of this method lies in the unlabeled nature of satellite imagery, which makes traditional ML frameworks impractical. Additionally, downloading the high-resolution satellite imagery for centralized ML is hindered by limited bandwidth and sporadic connectivity between the low Earth orbit (LEO) satellites and ground server. To address these challenges, we propose a novel semi-supervised federated learning framework named Semi-FedDA. It utilizes a small amount of labeled data on the ground server and a large amount of unlabeled data on the satellites to efficiently train a building assessment model without manual labeling. Moreover, this framework leverages intra-plane inter-satellite links (ISLs) to implement intra-orbit aggregations, which can significantly reduce the communication cost. We conduct extensive experiments on the real-world dataset. Numerical results show that our proposed framework can reduce training time by up to 94% compared with baselines, without sacrificing model accuracy.

Text-to-image generative models have garnered immense attention for their ability to produce high-fidelity images from text prompts. Among these, Stable Diffusion distinguishes itself as a leading open-source model in this fast-growing field. However, the intricacies of fine-tuning these models pose multiple challenges from new methodology integration to systematic evaluation. Addressing these issues, this paper introduces LyCORIS (Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion), an open-source library that offers a wide selection of fine-tuning methodologies for Stable Diffusion. Furthermore, we present a thorough framework for the systematic assessment of varied fine-tuning techniques. This framework employs a diverse suite of metrics and delves into multiple facets of fine-tuning, including hyperparameter adjustments and the evaluation with different prompt types across various concept categories. Through this comprehensive approach, our work provides essential insights into the nuanced effects of fine-tuning parameters, bridging the gap between state-of-the-art research and practical application.

Federated Learning (FL) is a collaborative learning framework that enables edge devices to collaboratively learn a global model while keeping raw data locally. Although FL avoids leaking direct information from local datasets, sensitive information can still be inferred from the shared models. To address the privacy issue in FL, differential privacy (DP) mechanisms are leveraged to provide formal privacy guarantee. However, when deploying FL at the wireless edge with over-the-air computation, ensuring client-level DP faces significant challenges. In this paper, we propose a novel wireless FL scheme called private federated edge learning with sparsification (PFELS) to provide client-level DP guarantee with intrinsic channel noise while reducing communication and energy overhead and improving model accuracy. The key idea of PFELS is for each device to first compress its model update and then adaptively design the transmit power of the compressed model update according to the wireless channel status without any artificial noise addition. We provide a privacy analysis for PFELS and prove the convergence of PFELS under general non-convex and non-IID settings. Experimental results show that compared with prior work, PFELS can improve the accuracy with the same DP guarantee and save communication and energy costs simultaneously.

Federated learning (FL) that enables edge devices to collaboratively learn a shared model while keeping their training data locally has received great attention recently and can protect privacy in comparison with the traditional centralized learning paradigm. However, sensitive information about the training data can still be inferred from model parameters shared in FL. Differential privacy (DP) is the state-of-the-art technique to defend against those attacks. The key challenge to achieving DP in FL lies in the adverse impact of DP noise on model accuracy, particularly for deep learning models with large numbers of parameters. This paper develops a novel differentially-private FL scheme named Fed-SMP that provides a client-level DP guarantee while maintaining high model accuracy. To mitigate the impact of privacy protection on model accuracy, Fed-SMP leverages a new technique called Sparsified Model Perturbation (SMP) where local models are sparsified first before being perturbed by Gaussian noise. We provide a tight end-to-end privacy analysis for Fed-SMP using Rényi DP and prove the convergence of Fed-SMP with both unbiased and biased sparsifications. Extensive experiments on real-world datasets are conducted to demonstrate the effectiveness of Fed-SMP in improving model accuracy with the same DP guarantee and saving communication cost simultaneously.

Participant selection (PS) helps to accelerate federated learning (FL) convergence, which is essential for the practical deployment of FL over mobile devices. While most existing PS approaches focus on improving training accuracy and efficiency rather than residual energy of mobile devices, which fundamentally determines whether the selected devices can participate. Meanwhile, the impacts of mobile devices heterogeneous wireless transmission rates on PS and FL training efficiency are largely ignored. Moreover, PS causes the staleness issue. Prior research exploits isolated functions to force long-neglected devices to participate, which is decoupled from original PS designs. In this paper, we propose aresidualenergy andwirelessaware PS design for efficientFLtraining over mobile devices (REWAFL). REWAFL introduces a novel PS utility function that jointly considers global FL training utilities and local energy utility, which integrates energy consumption and residual battery energy of candidate mobile devices. Under the proposed PS utility function framework, REWAFL further presents a residual energy and wireless aware local computing policy. Besides, REWAFL buries the staleness solution into its utility function and local computing policy. The experimental results show that REWAFL is effective in improving training accuracy and efficiency, while avoiding flat battery of mobile devices.

Federated learning (FL) enables collaborative model training without centralizing data. However, the traditional FL framework is cloud-based and suffers from high communication latency. On the other hand, the edge-based FL framework that relies on an edge server co-located with mobile base station for model aggregation has low communication latency but suffers from degraded model accuracy due to the limited coverage of edge server. In light of high-accuracy but high-latency cloud-based FL and low-latency but low-accuracy edge-based FL, this paper proposes a new FL framework based on cooperative mobile edge networking called cooperative federated edge learning (CFEL) to enable both high-accuracy and low-latency distributed intelligence at mobile edge networks. Considering the unique two-tier network architecture of CFEL, a novel federated optimization method dubbed cooperative edge-based federated averaging (CE-FedAvg) is further developed, wherein each edge server both coordinates collaborative model training among the devices within its own coverage and cooperates with other edge servers to learn a shared global model through decentralized consensus. Experimental results based on benchmark datasets show that CFEL can largely reduce the training time to achieve a target model accuracy compared with prior FL frameworks.

Users in dynamic spectrum access (DSA) with federated reinforcement learning (FRL) autonomously access channels, avoiding centralized coordination and protecting users’ privacy. However, existing FRL-based DSA mechanisms are limited to ideal network states, i.e., assuming that channel states and users’ interference relationships are unchanged. Besides, users should upload intermediate results simultaneously for federated aggregation. The above conditions are impractical for mobile users since their network states and locations are unstable. Meanwhile, newly connected users have to train their models through local data with numerous computing resources since global models are unsuitable for them. We propose FRDSA, an FRL-based secure and lightweight channel selection mechanism in DSA for mobile users under dynamic network states. An independent channel selection environment with a virtual group strategy is presented to avoid interference between users under unstable channel states. Furthermore, an asynchronous parameter aggregation method in FRDSA dynamically adjusts the aggregation factors without users simultaneously uploading intermediate results. Simulations based on real trajectory data show that FRDSA significantly reduces approximately 60% interference between mobile users under unstable network states. Newly connected users can directly apply the well-trained global model to access channels autonomously instead of retraining a model, effectively reducing mobile users’ computing resource requirements.

Federated learning (FL) over mobile devices is an emerging distributed learning paradigm for numerous delay sensitive applications. In FL, the training delay is composed of the computing and communication delay. Some of the participating mobile devices may have slow local computing or wireless communications, which results in high FL training delay. Intuitively, if fast devices help slow ones, the FL training delay can potentially be reduced. However, helping each other among devices requires frequent transmissions and may cause additional delay. Fortunately, we observe that Device-to-Device (D2D) transmission, a fast and direct transmission, may be applied between device pairs to mitigate the additional delay from frequent transmissions. Inspired by those observations, we develop the D2D transmission assisted FL (DAFL), a novel FL scheme to improve the training delay over mobile devices. Briefly, we first put the eligible mobile devices into pairs, each pair consisting of a fast and a slow device. Then, we apply D2D transmission between each device pair to: (1) improve the transmission delay of each pair, by letting the fast device help with the model parameters transmission to the server, and (2) improve the computing delay by splitting learning task between paired devices. The emulation results demonstrate that DAFL surpasses existing peer designs in terms of reducing training delay by more than 20%.

The scheduling problem for federated learning (FL) with multiple models in a distributed network is challenging, as it involves NP-hard mixed-integer nonlinear programming. Moreover, it requires optimal participant selection and learning rate determination among multiple FL models to avoid high training costs and resource competition. To overcome those chal-lenges, in literature the Benders' decomposition algorithm (BD) can deal with mixed integer problems, however, it still suffers from limited scalability. To address this issue, in this paper, we present the Hybrid Quantum-Classical Benders' Decomposition (HQCBD) algorithm, which combines the power of quantum and classical computing to solve the joint participant selection and learning scheduling problem in multi-model FL. HQCBD decomposes the optimization problem into a master problem with binary variables and small subproblems with continuous variables. This collaboration maximizes the potential of both quantum and classical computing, and optimizes the complex joint optimization problem. Simulation on the commercial D-Wave quantum annealing machine demonstrates the effectiveness and robustness of the proposed method, with up to 18% improvement of iterations and 81% improvement of computation time over BD algorithm on classical CPUs even at small scales.

Federated learning (FL) over mobile edge devices is a promising distributed learning paradigm for various mobile applications. However, practical deployment of FL over mobile devices is very challenging because (i) conventional FL incurs huge training latency for mobile edge devices due to interleaved local computing and communications of model updates, (ii) there are heterogeneous training data across mobile edge devices, and (iii) mobile edge devices have hardware heterogeneity in terms of computing and communication capabilities.To address aforementioned challenges, in this paper, we propose a novel "workie-talkie" FL scheme, which can accelerate FL’s training by overlapping local computing and wireless communications via contrastive regularization (FedCR). FedCR can reduce FL’s training latency and almost eliminate straggler issues since it buries/embeds the time consumption of communications into that of local training. To resolve the issue of model staleness and data heterogeneity co-existing, we introduce class-wise contrastive regularization to correct the local training in FedCR. Besides, we jointly exploit contrastive regularization and subnetworks to further extend our FedCR approach to accommodate edge devices with hardware heterogeneity. We deploy FedCR in our FL testbed and conduct extensive experiments. The results show that FedCR outperforms its status quo FL approaches on various datasets and models.

Auction is becoming increasingly popular for dynamic spectrum access (DSA), while it is extremely vulnerable to sybil attacks. Existing studies on sybil-proof DSA auction impractically assume that attackers bid truthfully based on true appraisals. This paper, for the first time, considers untruthful attackers and investigates the sybil-proof auction design in such more hazardous scenarios. To justify the new assumption, we first show that attackers obtain higher utilities by bidding untruthfully, especially in networks with inadequate channels. Based on this novel finding, we then design a practical sybil attack model named EqualSumBid Sybil, where attackers follow an equal-sum rule (i.e., the sum bid value of the multiple identities of an attacker equals the bid value when it bids with only one identity) instead of their true appraisals. To ensure efficient DSA under the new attack, we finally propose the PRAM, a Practical sybil-pRoof Auction Mechanism, where suspicious identity merging and bid-independent bidder sorting methods are introduced to alleviate the effect of untruthfulness on spectrum auction. Furthermore, winner selection and payment methods are designed to resist the EqualSumBid Sybil attack. Theoretical analyses and numerical results show that PRAM not only resists the EqualSumBid Sybil attack but also achieves individual rationality and truthfulness.

This paper considers a federated edge learning (FEL) system where a base station (BS) coordinates a set of edge devices to train a shared machine learning model collaboratively. One of the fundamental issues in such systems is maintaining the learning performance with the limited and heterogeneous resource capabilities of edge devices. Our goal is to improve the energy efficiency of edge devices in FEL by mitigating the temporal and spatial heterogeneity of their energy resources. Specifically, to balance the heterogeneous energy levels among edge devices, energy-hungry devices can offload their data to nearby devices that have sufficient energy via device-to-device (D2D) communication links at low transmission overheads. Be-sides, to mitigate the impact of the time-varying energy level of a device, data collected by edge devices can be queued to be processed when sufficient energy is available. To compute the optimal offloading and queuing strategies, we propose an online control algorithm based on Lyapunov optimization to determine the amount of data to be offloaded, queued, and processed at each time slot. Our simulation results on the real-world dataset demonstrate that our approach achieves a better overall energy efficiency than baselines.

Preventing COVID-19 disease from spreading in communities will require proactive and effective healthcare resource allocations, such as vaccinations. A fine-grained COVID-19 vulnerability map will be essential to detect the high-risk communities and guild the effective vaccine policy. A mobile-crowdsourcing-based self-reporting approach is a promising solution. However, an accurate mobile-crowdsourcing-based map construction requests participants to report their actual locations, raising serious privacy concerns. To address this issue, we propose a novel approach to effectively construct a reliable community-level COVID-19 vulnerability map based on mobile crowdsourced COVID-19 self-reports without compromising participants’ location privacy. We design a geo-perturbation scheme where participants can locally obfuscate their locations with the geo-indistinguishability guarantee to protect their location privacy against any adversaries’ prior knowledge. To minimize the data utility loss caused by location perturbation, we first design an unbiased vulnerability estimator and formulate the location perturbation probability generation into a convex optimization. Its objective is to minimize the estimation error of the direct vulnerability estimator under the constraints of geo-indistinguishability. Given the perturbed locations, we integrate the perturbation probabilities with the spatial smoothing method to obtain reliable community-level vulnerability estimations that are robust to a small-sampling-size problem incurred by location perturbation. Considering the fast-spreading nature of coronavirus, we integrate the vulnerability estimates into the modified susceptible-infected-removed (SIR) model with vaccination for building a future trend map. It helps to provide a guideline for vaccine allocation when supply is limited. Extensive simulations based on real-world data demonstrate the proposed scheme superiority over the peer designs satisfying geo-indistinguishability in terms of estimation accuracy and reliability.

Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. However, data locality does not provide sufficient privacy protection, and it is desirable to facilitate FL with rigorous differential privacy (DP) guarantee. Existing DP mechanisms would introduce random noise with magnitude proportional to the model size, which can be quite large in deep neural networks. In this paper, we propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee. Since sparsification would increase the number of communication rounds required to achieve a certain target accuracy, which is unfavorable for DP guarantee, we further introduce acceleration techniques to help reduce the privacy cost. We rigorously analyze the convergence of our approach and utilize Renyi DP to tightly account the end-to-end DP guarantee. Extensive experiments on benchmark datasets validate that our approach outperforms previous differentially-private FL approaches in both privacy guarantee and communication efficiency.

In this paper, we study how colocation datacenter energy cost can be effectively reduced in the wholesale electricity market via cooperative power procurement. Intuitively, by aggregating workloads and renewables across a group of tenants in a colocation datacenter, the overall power demand uncertainty of the colocation datacenter can be reduced, resulting in less chance of being penalized when participating in the wholesale electricity market. We use cooperative game theory to model the cooperative electricity procurement process of tenants as a cooperative game, and show the cost saving benefits of aggregation. Then, a cost allocation scheme based on the marginal contribution of each tenant to the total expected cost is proposed to distribute the aggregation benefits among the participating tenants. Besides, we propose proportional cost allocation scheme to distribute the aggregation benefits among the participating tenants after realizations of power demand and market prices. Finally, numerical experiments based on real-world traces are conducted to illustrate the benefits of aggregation compared to noncooperative power procurement.

The aim of this paper is to preserve location privacy of crowdsourced-based spectrum sensing agents using geo-indistinguishability. We considered database-driven dynamic spectrum access, where a radio environment map provides spectrum availability information for dynamic spectrum access management. Moreover, we assumed crowdsourced-based spectrum sensing, where a pool of allocated mobile users, called crowdsourced-based spectrum sensing agents, sense the spectrum and report their actual location and the received signal strength to the spectrum manager that constructs a radio environment map. This discloses location information of crowdsourced-based spectrum sensing agents and violates their location privacy. Consequently, crowdsourced-based spectrum sensing agents could be discouraged to participate in spectrum sensing. In our paper, to solve the problem of location disclosure, we adopted planar Laplacian mechanism, where each crowdsourced-based spectrum sensing agent reports an obfuscated location instead of its actual location, which achieves geo-indistinguishability. Our simulation results were based on real-world CRAWDAD dataset. Our results showed that with a moderate privacy level, location privacy of crowdsourced-based spectrum sensing agents was preserved while the effect of introduced location noise on the accuracy of radio environment map was insignificant.

The pandemic of the coronavirus (COVID-19) has caused an unprecedented global public health crisis, and most countries in the world are running out of the healthcare resources. A fine-grained COVID-19 vulnerability map will be essential to track the number of people with covid-like symptoms, so that the the potential outbreak communities can be identified and the valuable healthcare resources can proactively and dynamically be allocated. Mobile crowdsourcing based symptom reporting is a promising and convenient option to construct such a map, while it may compromise the location privacy of crowdsourcing participants. In this work, we propose a novel approach to establish the COVID-19 vulnerability map based on the crowdsourced reporting without disclosing the participants' location privacy to a semi-honest crowdsourcing aggregator. Briefly, based on the differentially private geo-indistinguishability, the mobile participants are able to locally perturb their geographic data. With the masked geographic information, we employ the best linear unbiased prediction estimator with spatial smoothing to obtain the reliable vulnerability estimates in the areas of interest and construct the map. Given the fast spreading nature of coronavirus, we integrate the vulnerability estimates with a susceptible-exposed-infected-removed (SEIR) model to build up a future trend map. Extensive simulations based on real-world data verify the effectiveness of the proposed method.

Graph classification has practical applications in diverse fields. Recent studies show that graph-based machine learning models are especially vulnerable to adversarial perturbations due to the non i.i. d nature of graph data. By adding or deleting a small number of edges in the graph, adversaries could greatly change the graph label predicted by a graph classification model. In this work, we propose to build a smoothed graph classification model with certified robustness guarantee. We have proven that the resulting graph classification model would output the same prediction for a graph under l0bounded adversarial perturbation. We also evaluate the effectiveness of our approach under graph convolutional network (GCN) based multi-class graph classification model.

Federated Learning rests on the notion of training a global model distributedly on various devices. Under this setting, users' devices perform computations on their own data and then share the results with the cloud server to update the global model. A fundamental issue in such systems is to effectively incentivize user participation. The users suffer from privacy leakage of their local data during the federated model training process. Without well-designed incentives, self-interested users will be unwilling to participate in federated learning tasks and contribute their private data. To bridge this gap, in this paper, we adopt the game theory to design an effective incentive mechanism, which selects users that are most likely to provide reliable data and compensates for their costs of privacy leakage. We formulate our problem as a two-stage Stackelberg game and solve the game's equilibrium. Effectiveness of the proposed mechanism is demonstrated by extensive simulations.

To provide intelligent and personalized services on smart devices, machine learning techniques have been widely used to learn from data, identify patterns, and make automated decisions. Machine learning processes typically require a large amount of representative data that are often collected through crowdsourcing from end users. However, user data could be sensitive in nature, and learning machine learning models on these data may expose sensitive information of users, violating their privacy. Moreover, to meet the increasing demand of personalized services, these learned models should capture their individual characteristics. This paper proposes a privacy-preserving approach for learning effective personalized models on distributed user data while guaranteeing the differential privacy of user data. Practical issues in a distributed learning system such as user heterogeneity are considered in the proposed approach. Moreover, the convergence property and privacy guarantee of the proposed approach are rigorously analyzed. Experiments on realistic mobile sensing data demonstrate that the proposed approach is robust to high user heterogeneity and offer a trade-off between accuracy and privacy.

To provide intelligent and personalized services on smart devices, machine learning techniques have been widely used to learn from data, identify patterns, and make automated decisions. Machine learning processes typically require a large amount of representative data that are often collected through crowdsourcing from end users. However, user data could be sensitive in nature, and training machine learning models on these data may expose sensitive information of users, violating their privacy. Moreover, to meet the increasing demand of personalized services, these learned models should capture their individual characteristics. This article proposes a privacy-preserving approach for learning effective personalized models on distributed user data while guaranteeing the differential privacy of user data. Practical issues in a distributed learning system such as user heterogeneity are considered in the proposed approach. In addition, the convergence property and privacy guarantee of the proposed approach are rigorously analyzed. The experimental results on realistic mobile sensing data demonstrate that the proposed approach is robust to user heterogeneity and offers a good tradeoff between accuracy and privacy.

Mobile edge computing (MEC) is an emerging technology to support resource-intensive yet delay-sensitive applications using small cloud-computing platforms deployed at the mobile network edges. However, the existing MEC techniques are not applicable to the situation where the number of mobile users increases explosively or the network facilities are sparely distributed. In view of this insufficiency, unmanned aerial vehicles (UAVs) have been employed to improve the connectivity of ground Internet of Things (IoT) devices due to their high altitude. This article proposes an innovative UAV-enabled MEC system involving the interactions among IoT devices, UAV, and edge clouds (ECs). The system deploys and operates a UAV properly to facilitate the MEC service provisioning to a set of IoT devices in regions where the existing ECs cannot be accessible to IoT devices due to terrestrial signal blockage or shadowing. The UAV and ECs in the system collaboratively provide MEC services to the IoT devices. For optimal service provisioning in this system, we formulate an optimization problem aiming at minimizing the weighted sum of the service delay of all IoT devices and UAV energy consumption by jointly optimizing UAV position, communication and computing resource allocation, and task splitting decisions. However, the resulting optimization problem is highly nonconvex and thus, difficult to solve optimally. To tackle this problem, we develop an efficient algorithm based on the successive convex approximation to obtain suboptimal solutions. Numerical experiments demonstrate that our proposed collaborative UAV-EC offloading scheme largely outperforms baseline schemes that solely rely on UAV or ECs for MEC in IoT.

Alternating direction method of multipliers (ADMM) is a widely used tool for machine learning in distributed settings where a machine learning model is trained over distributed data sources through an interactive process of local computation and message passing. Such an iterative process could cause privacy concerns of data owners. The goal of this paper is to provide differential privacy for ADMM-based distributed machine learning. Prior approaches on differentially private ADMM exhibit low utility under high privacy guarantee and assume the objective functions of the learning problems to be smooth and strongly convex. To address these concerns, we propose a novel differentially private ADMM-based distributed learning algorithm called DP-ADMM, which combines an approximate augmented Lagrangian function with time-varying Gaussian noise addition in the iterative process to achieve higher utility for general objective functions under the same differential privacy guarantee. We also apply the moments accountant method to analyze the end-to-end privacy loss. The theoretical analysis shows that the DP-ADMM can be applied to a wider class of distributed learning problems, is provably convergent, and offers an explicit utility-privacy tradeoff. To our knowledge, this is the first paper to provide explicit convergence and utility properties for differentially private ADMM-based distributed learning algorithms. The evaluation results demonstrate that our approach can achieve good convergence and model accuracy under high end-to-end differential privacy guarantee.

With the popularity of online social networks, social recommendations that rely on ones social connections to make personalized recommendations have become possible. This introduces vulnerabilities for an adversarial party to compromise the recommendations for users by utilizing their social connections. In this paper, we propose the targeted poisoning attack on the factorization-based social recommender system in which the attacker aims to promote an item to a group of target users by injecting fake ratings and social connections. We formulate the optimal poisoning attack as a bi-level program and develop an efficient algorithm to find the optimal attacking strategy. We then evaluate the proposed attacking strategy on real-world dataset and demonstrate that the social recommender system is sensitive to the targeted poisoning attack. We find that users in the social recommender system can be attacked even if they do not have direct social connections with the attacker.

Nowadays most mobile devices are equipped with advanced sensors, enabling the measurement of information about surrounding environment or social settings. The ubiquity of mobile devices makes them the perfect platform for massive data collection, which motivates the emergence of mobile crowdsensing paradigm. However, due to the inherent noisy nature of the sensing process and the limited capability of low-cost commodity sensors, crowdsensed information tends to be less reliable compared with sensing results through dedicated sensing hardware, and multiple crowdsensing sources may conflict with each other. Thus, it is important to resolve conflicts in the collected data and discover the underlying truth. Traditional truth discovery approaches usually estimate the reliability of data sources and predict the truth value based on source reliability. However, recent data poisoning attacks greatly degrade the performance of existing truth discovery algorithms, where attackers aim to maximize the utility loss. In this paper, we investigate the data poisoning attacks on truth discovery and propose a robust approach against such attacks through additional source estimation and source filtering before data aggregation. Based on real-world data, we simulate our approach and evaluate its performance under data poisoning attacks, demonstrating the robustness of our approach.

In this paper, we investigate the issue of resource allocation for secure energy efficient communication in a multiuser orthogonal frequency division multiplexing (OFDM) based full-duplex (FD) relaying network in the presence of a passive eavesdropper whose channel state information (CSI) is not perfectly known. Our goal is to maximize the overall secure energy efficiency (SEE), which presents the relationship between energy consumption and secrecy performance. In the context of multiuser communications, such a resource allocation strategy jointly combines subcarrier permutation, subcarrier pair allocation, as well as power allocation altogether. The considered optimization problem is formulated as a mixed integer nonconvex programming problem, which is generally NP hard. Analyzing the property of such a problem, we first use the Dinkelbach's method to eliminate the fractional form and then exploit Generalized Benders decomposition to decouple the original problem into a master problem for pure integer programming and a primal problem for nonlinear programming. More specific, given the nonconvexity of the primal problem, we accordingly transform it into an equivalent relaxed convex problem by applying dual decomposition, alternative convex search, and difference of convex function programming. The numerical results are provided to validate the theoretical analysis and to demonstrate the effectiveness of the proposed algorithm.

Colocation data centers are an important type of data centers that have some unique challenges in managing their energy consumption. Tenants in a colocation data center usually manage their servers independently without coordination, leading to inefficiency. To address this issue, we propose a formulation of coordinated energy management for colocation data centers. Considering the randomness of workload arrival and electricity cost function, we formulate it as a stochastic optimization problem, and then develop an online algorithm to solve it efficiently. Our algorithm is based on Lyapunov optimization, which only needs to track the instantaneous values of the underlying random factors without requiring any knowledge of the statistics or future information. Moreover, alternating direction method of multipliers (ADMM) is utilized to implement our algorithm in a decentralized way, making it easy to be implemented in practice. We analyze the performance of our online algorithm, proving that it is asymptotically optimal and robust to the statistics of the involved random factors. Moreover, extensive trace-based simulations are conducted to illustrate the effectiveness of our approach.

With the growth of smartphone sales and app usage, fingerprinting and identification of smartphone apps have become a considerable threat to user security and privacy. Traffic analysis is one of the most common methods for identifying apps. Traditional countermeasures towards traffic analysis includes traffic morphing and multipath routing. The basic idea of multipath routing is to increase the difficulty for adversary to eavesdrop all traffic by splitting traffic into several subflows and transmitting them through different routes. Previous works in multipath routing mainly focus on Wireless Sensor Networks (WSNs) or Mobile Ad Hoc Networks (MANETs). In this paper, we propose a multipath routing scheme for smartphones with edge network assistance to mitigate traffic analysis attack. We consider an adversary with limited capability, that is, he can only intercept the traffic of one node following certain attack probability, and try to minimize the traffic an adversary can intercept. We formulate our design as a flow routing optimization problem. Then a heuristic algorithm is proposed to solve the problem. Finally, we present the simulation results for our scheme and justify that our scheme can effectively protect smartphones from traffic analysis attack.

Website fingerprinting attacks have been shown to be able to predict the website visited even if the network connection is encrypted and anonymized. These attacks have achieved accuracies as high as 92%. Mitigations to these attacks are using cover/decoy network traffic to add noise, padding to ensure all the network packets are the same size, and introducing network delays to confuse an adversary. Although these mitigations have been shown to be effective, reducing the accuracy to 10%, the overhead is very high. The latency overhead is above 100% and the bandwidth overhead is at least 40%. We introduce a new realistic cover traffic algorithm, based on a user's previous network traffic, to mitigate website fingerprinting attacks. In simulations, our algorithm reduces the accuracy of attacks to 14% with zero latency overhead and about 20% bandwidth overhead.

Smart homes (SHs) aim at forming an energy optimized environment that can efficiently regulate the use of various Internet of Things (IoT) devices in its network. Real-time electricity pricing models along with SHs provide users an opportunity to reduce their electricity expenditure by responding to the pricing that varies with different times of the day, resulting in reducing the expenditure at both customers’ and utility provider’s end. However, responding to such prices and effectively scheduling the appliances under such complex dynamics is a challenging optimization problem to be solved by the provider or by third party services. As communication in SH-IoT environment is extremely sensitive and private, reporting of such usage information to the provider to solve the optimization has a potential risk that the provider or third party services may track users’ energy consumption profile which compromises users’ privacy. To address these issues, we developed a homomorphic encryption-based alternating direction method of multipliers approach to solve the cost-aware appliance scheduling optimization in a distributed manner and schedule home appliances without leaking users’ privacy. Through extensive simulation study considering real-world datasets, we show that the proposed secure appliance scheduling for flexible and efficient energy consumption scheme, namely SAFE, effectively lowers electricity cost while preserving users’ privacy.

Recently opened spectrum within 3550-3700 MHz provides more accessing opportunities to secondary users (SUs), while it also raises concerns on the operational privacy of primary users (PUs), especially for military and government. In this paper, we propose to study the tradeoff between PUs' temporal privacy and SUs' network performance using the data-driven approach. To preserve PUs' temporal operational privacy, we develop an obfuscation strategy for PUs, which allows PUs to intentionally add dummy signals to change the distribution of temporal spectrum availability, and confuse the adversary. While generating the dummy signals for privacy, the PUs have to consider the utility of SUs and try their best to satisfy SUs' uncertain traffic demands. Based on the historical data, we employ a data-driven risk-averse model to characterize the uncertainty of SUs' demands. With joint consideration of PUs' privacy and uncertain SUs' demands, we formulate the data-driven risk- averse stochastic optimization, and provide corresponding solutions. Through numerical simulations, we show that the proposed scheme is effective in preserving PUs' temporal operational privacy while offering good enough spectrum resources to satisfy SUs' traffic demands.

Using genetic profiles of individuals for tailored diagnosis and treatment has great promise in the healthcare industry. Despite of the rapid growth in genome-aware medicine, genome-aware health monitoring has not been studied as well. A major stumbling block is the privacy issues of such applications. In addition to privacy concerns in a traditional health monitoring system, i.e., the privacy of users' biomedical sensing data and the protection of the proprietary health monitoring program, severe privacy concerns arise when users' genomic data are integrated into the health monitoring program due to the re-identification and phenotype attacks based on the DNA profile and the relevance of DNA information in a family. In this paper, we investigate these privacy risks and propose a privacy- preserving approach for genome-aware health monitoring. In our approach, users can only learn the diagnostic results based on their genomic and biomedical sensing data, while the the healthcare service provider learns nothing. Security analysis and performance evaluations are conducted to illustrate the effectiveness and efficiency of the proposed approach.

It is increasingly common for enterprises and other organizations to outsource firewalls to public clouds in order to reduce the cost and complexity in deploying and maintaining dedicated hardware middleboxes. However, this poses a serious threat to the enterprise network security because sensitive network policies, such as firewall rules, are revealed to cloud providers, which may be leaked and exploited by attackers. In this paper, we design and implement a SE- FWaaS, a secured system that enables cloud providers to support middlebox (e.g., firewall) outsourcing while preserving the network policy confidentiality. The key ingredients in our SE-FWaaS are the distribution of the firewall primitives, namely policy checking and verdict enforcing, to two independent public clouds, and the enabling techniques of efficient firewall rule obfuscation and oblivious rule-matching. Our SE-FWaaS provides the maximum achievable level of protection of network policies by enforcing the principle of the least privilege and removing the threat of offline probing attacks. We evaluate the proposed system over real-world firewall rules and demonstrate its effectiveness and feasibility.

Mobile crowdsourcing (MC) is a transformative paradigm that engages a crowd of mobile users (i.e., workers) in the act of collecting, analyzing, and disseminating information or sharing their resources. To ensure quality of service, MC platforms tend to recommend MC tasks to workers based on their context information extracted from their interactions and smartphone sensors. This raises privacy concerns hard to address due to the constrained resources on mobile devices. In this paper, we identify fundamental tradeoffs among three metrics-utility, privacy, and efficiency-in an MC system and propose a flexible optimization framework that can be adjusted to any desired tradeoff point with joint efforts of MC platform and workers. Since the underlying optimization problems are NP-hard, we present efficient approximation algorithms to solve them. Since worker statistics are needed when tuning the optimization models, we use an efficient aggregation approach to collecting worker feedbacks while providing differential privacy guarantees. Both numerical evaluations and performance analysis are conducted to demonstrate the effectiveness and efficiency of the proposed framework.

Advances in biomedical sensors and mobile communication technologies have fostered the rapid growth of mobile health (mHealth) applications in the past years. Users generate a high volume of biomedical data during health monitoring, which can be used by the mHealth server for training predictive models for disease diagnosis and treatment. However, the biomedical sensing data raise serious privacy concerns because they reveal sensitive information such as health status and lifestyles of the sensed subjects. This paper proposes and experimentally studies a scheme that keeps the training samples private while enabling accurate construction of predictive models. We specifically consider logistic regression models which are widely used for predicting dichotomous outcomes in healthcare, and decompose the logistic regression problem into small subproblems over two types of distributed sensing data, i.e., horizontally partitioned data and vertically partitioned data. The subproblems are solved using individual private data, and thus mHealth users can keep their private data locally and only upload (encrypted) intermediate results to the mHealth server for model training. Experimental results based on real datasets show that our scheme is highly efficient and scalable to a large number of mHealth users.

Health monitoring is an important category of mobile Health (mHealth) applications. Users generate a large volume of data during health monitoring, which can then be used by the mHealth server for constructing diagnosis or prognosis prediction models. However, these training samples contain private information of data owners, who may be reluctant to share them with the mHealth server. This paper proposes and experimentally studies a scheme that keeps the training samples private while enabling accurate construction of diagnosis and prognosis models. We specifically consider logistic regression models which are widely used in mHealth, and decompose the logistic regression model construction problem into small subproblems that can be executed by each user using their own private data. In this manner, users can keep their raw data locally and only upload encrypted parameters to the mHealth server for model construction. We show that our scheme suits well in mHealth applications by conducting experimental evaluations based on a real-world dataset and analyzing its computation overhead.

Mobile crowdsourcing enables mobile workers to complete a broad range of crowdsourcing tasks anywhere at any time. However, recommending suitable crowdsourcing tasks to mobile workers requires sensitive information such as location and activity, which raises serious privacy concerns. In this paper, we formulate the task recommendation process as an optimization problem which balances privacy, utility, and efficiency. We show that this optimization problem is NP-hard, and present a greedy solution which approximates the optimal solution within a factor of 1 - 1/e. We also design an efficient aggregation protocol to compute statistics of mobile workers required in the optimization problem while providing strong privacy guarantee. Both numerical evaluations and performance analysis are carried out to show the effectiveness and efficiency of the proposed framework. To the best of our knowledge, our work is the first to consider privacy issues in task recommendation for mobile crowdsourcing.

Reducing the carbon footprint of data centers is becoming a primary goal of large IT companies. Unlike traditional energy sources, renewable energy sources are usually intermittent and unpredictable. How to better utilize the green energy from these renewable sources in data centers is a challenging problem. In this paper, we exploit the opportunities offered by geographical load balancing, opportunistic scheduling of delay-tolerant workloads, and thermal storage management in data centers to facilitate green energy integration and reduce the cost of brown energy usage. Moreover, bandwidth cost variations between users and data centers are considered. Specifically, this problem is first formulated as a stochastic program, and then, an online control algorithm based on the Lyapunov optimization technique, called Stochastic Cost Minimization Algorithm (SCMA), is proposed to solve it. The algorithm can enable an explicit trade-off between cost saving and workload delay. Numerical results based on real-world traces illustrate the effectiveness of SCMA in practice.

Reducing the carbon footprint of data centers is becoming a primary goal of large IT companies. Due to the intermittency and unpredictability of renewable energy sources such as wind and solar, it is quite challenging to utilize them in data centers. In this paper, we explore the opportunities offered by delay-tolerant workloads and thermal storage to facilitate the renewable energy integration in data centers and meanwhile, reduce the cost of using brown energy (i.e., energy from the utility grid). A stochastic optimization problem is formulated to tackle the stochastic renewable generation and workload arrival processes. Then, an online control algorithm based on the Lyapunov optimization approach is proposed to solve it. Simulation results based on the real-world traces show the effectiveness of the algorithm in practice.

In this paper, we address the problem of score fusion in biometric authentication. Single valued metrics related to the receiver operating characteristics (ROC) curve, such as Equal Error Rate (EER) and False Rejection Rate (FRR) when False Acceptance Rate equals zero, are extensively used for evaluating biometric authentication performances. Various requirements and preferences, for example, lower EER, or smaller FRR, may be imposed on biometric authentication systems in different application scenarios. We propose a novel method of score fusion based on quasi-convex optimization to directly improve biometric authentication metrics. Experiments based on a face recognition system demonstrate the effectiveness of the proposed method.