Abstract To address the storage overhead of lightmaps and the limitations of existing compression techniques, we propose a novel UV‐space compression framework based on per‐triangle processing. By mapping triangles to a standardized domain, we cluster and repack color‐coherent regions into a compact atlas, generating a cascade texture refined via differentiable rendering. Experimental results show an average storage reduction of 83% with approximately 10 dB higher PSNR than existing methods. Our approach is the first dedicated lightmap compression framework compatible with standard block‐based formats, offering an effective solution for memory‐efficient 3D asset delivery.

In recent years, sensor-based continuous authentication on mobile devices has emerged as a promising solution for enhancing personal information security. However, many existing approaches depend on both legitimate and illegitimate user data for supervised training, which is time-consuming and often impractical in real-world deployments. To address these limitations, we propose CRAFTAuth, a sensor-based continuous Authentication system built upon Context Reconstruction and Adaptive Fusion Transformer. CRAFTAuth leverages built-in smartphone sensors of the accelerometer and gyroscope to capture behavioral biometrics in a non-intrusive manner. The system employs a self-supervised Transformer-based autoencoder to reconstruct long-term behavioral contexts from historical data, enabling the extraction of stable and discriminative features. To enhance adaptability, an iterative attention adaptive fusion mechanism dynamically integrates real-time behavioral inputs with long-term contextual features through progressive spatial-temporal refinement. In addition, a channel merging strategy is incorporated to compress feature representations and reduce computational complexity while preserving temporal dependencies, facilitating efficient deployment on resource-constrained mobile devices. Extensive experiments on our dataset demonstrate that CRAFTAuth achieves state-of-the-art performance, attaining 99.28% accuracy and 0.79% EER, while significantly reducing model size and inference latency compared with existing methods.

The vector database stores data as high-dimensional feature vectors. Some recently proposed attack techniques enable an adversary to launch feature vector inversion (FVI) attacks against vector databases. In FVI attacks, an adversary trains an FVI attack network to reconstruct the original private data from their feature vectors based on the assumption that an auxiliary dataset is available to the adversary. However, such a data-available assumption is too strong, making such FVI attacks unrealistic in many real-world scenarios. In this paper, we make the first systematic study on FVI attacks against vector databases in the data-free setting. To tackle the issue of no training data, we develop an output-to-input data generation technique that helps to generate synthetic fake samples for the FVI attack network training. In addition, to ensure the high quality of generated fake samples, we develop the accelerable complete bipartite graph (CBG) search strategy and the downstream-classifier-aided generator training strategy. Furthermore, as the key insight of this work, we find that the proposed output-to-input data generation technique can be employed to launch the other three ML attacks. Intriguingly, we find that the proposed FVI attack technique in the data-free setting can be directly employed to boost the attack performance of FVI attacks in the auxiliary-dataset-available setting. Finally, we propose and study defenses against the proposed attacks.

Transfer learning (TL) by fine-tuning (FT) has become a popular paradigm to address the challenges of limited training data and computing resources encountered in model training. This study reveals that this paradigm is susceptible to a new threat called model parasitic (MP) attack. By poisoning the dataset used for fine-tuning, MP attacks enable the finetuned model to execute an additional task (e.g., a specific classification task) designated by the attacker while still being able to execute the original task that the victim's fine-tuned model aims to offer. In addition, through MP attacks, the attacker can free-ride the victim's machine learning (ML) services at the cost of the victim. To design MP attacks, we innovatively propose multiple strategies including the dual-cluster strategy, the benign-to-poisoned example generation strategy, and the feature assignment loss (FAL)-guided controllable perturbation search strategy. Through intensive experiments, we precisely identify the factors that influence the MP attack performance. Finally, we investigate three possible defenses, shedding light on more effective defense design. Our code is available at GitHub

Recently, it has been a popular trend to use self-supervised learning to pre-train an encoder using a large number of unlabeled image pairs. The pre-trained encoder can serve as a feature extractor to build many downstream tasks for the downstream users (e.g., edge devices). However, users who download the pre-trained models from the public online hub might face a security risk called backdoor attack. Previous research has indicated that in a self-supervised learning context, a backdoor attack injects backdoors into a pre-trained image encoder. As a result, downstream classifiers constructed based on this image encoder will concurrently inherit the backdoor behavior. According to the research, the attacker is able to utilize a small square that is pasted at a specific position on the image to trigger the attack. For the users, such a way of triggering is very obvious and easy to discover. In this work, we aim to propose covert backdoor attacks to pre-trained encoders in self-supervised learning. We propose three ways to covertly trigger a backdoor attack. First, we use the light difference of the image as a trigger. We define a different light as the trigger, the backdoor will be triggered when the image is recognized in the defined light, but it will be recognized normally by the classifier in normal light. Second, we use a defined semantic physical thing as the trigger. The defined physical thing appearing in the image is not out of place. If it appears, the backdoor will be triggered. Third, we define a class as a trigger set (i.e., physical class). The random image in this class is used, the backdoor will be triggered. The emergence of this class is a natural fit with the scenario of the downstream task. We designed different loss functions for different methods and experimentally verified the effectiveness of our proposed methods.

In today’s digital era, ensuring the security of mobile devices is of critical importance. Sensor-based continuous authentication has emerged as an effective approach for protecting personal information on mobile devices. However, most existing systems rely primarily on time-domain features, overlooking valuable information from other domains and leading to incomplete feature representation. In this paper, we propose AMDFAuth, a deep reinforcement learning (DRL)-based Adaptive Multi-Domain Feature Fusion For continuous Authentication on smartphones that integrates a multi-domain feature extraction network with an adaptive feature fusion mechanism based on DRL. During user registration, AMDFAuth implicitly collects standardized behavioral data via built-in accelerometers and gyroscopes, and pre-trains a Diffusion Transformer (DiT) model. Through transfer learning, we integrate two additional feature extraction branches with the pre-trained DiT to construct a multi-domain network that captures time-domain, wavelet-domain, and key latent features. These features are then adaptively fused using DRL, enabling joint optimization of the feature extraction modules, fusion network, and an MLP classifier for user identification. During continuous authentication, real-time sensor data are collected and processed by the trained network and classifier to verify user identification. Extensive evaluations on our dataset demonstrate that AMDFAuth achieves 98.52% accuracy and an Equal Error Rate (EER) of 0.94% using a 2-second time window and 10 unseen users. These results highlight the system’s excellent accuracy, robustness, and generalization capability in real-world mobile authentication scenarios.

Federated Large Language Model (FedLLM) shows excellent potential in collaboratively training large language models (LLM) under the federated learning (FL) framework, which is benefiting from its privacy protection advantage. However, FedLLM faces the significant challenge of the non-IID problem. In the real world, there are often cross-source or even cross-domain language set data between IoT devices. To address the issue, we propose a new FedLLM framework FedALoRA via personalized and efficient parameter fine-tuning (PEFT). Specifically, the proposed scheme combines the personalized aggregation method and the LoRA method, which can adaptively aggregate the downloaded global model and local model to the local target on each client while ensuring low training costs. This adaptation initializes the local model before each iterative training, enabling clients to learn general knowledge while enhancing their understanding of their own domain knowledge. Extensive experiments and analysis on cross-domain non-IID settings and the financial datasets on Dirichlet non-IID settings demonstrate the effectiveness and superiority of FedALoRA.

Nowadays, with the widespread adoption of mobile devices, information security has become particularly important. Existing sensor-based continuous authentication systems ensure the security of mobile devices to some extent, but most have drawbacks, such as lacking end-to-end structure or requiring data from both legitimate users and imposters for training. In this article, we present RPWAEAuth, a sensor-based continuous Authentication system using Reconstruction Probability in Wasserstein AutoEncoder. RPWAEAuth implicitly collects user behavior patterns from the built-in accelerometer, gyroscope, and magnetometer of mobile devices. The Wasserstein autoencoder maps the sensor data into a continuous latent space close to a prior distribution and reconstructs them using reconstruction probability for better authentication. In the registration stage, RPWAEAuth collects and preprocesses the sensor data from a legitimate user for RPWAE training. In the authentication stage, when a user interacts with the device, RPWAEAuth collects and preprocesses the sensor data, and then feeds them into the trained RPWAE to generate a reconstruction probability. This probability is then compared with a predefined threshold for user authentication. We evaluate the performance of RPWAEAuth on our dataset in terms of the effectiveness of RPWAEAuth, impact of sensor numbers, effectiveness of reconstruction probability, authentication time, resilience to mimic attacks, comparison with different AEs, and comparison with state-of-the-art methods. The experimental results demonstrate that RPWAEAuth achieves superior authentication performance compared to other methods, with an accuracy of 99.34% and an EER of 0.66% on 69 unseen users.

Face alignment is a critical and difficult task for many facial analysis applications. Existing VFA methods frequently ignore the consistency of facial geometries and textures across video sequences, limiting their ability to handle accurate and stable face alignment. This paper describes a robust and highly accurate 3D Morphable Model (3DMM)-based VFA approach that employs a novel texture generation method and a self-refined face alignment procedure. Our method iteratively fine-tunes facial geometries, textures, and poses by using a differentiable rendering technique and a self-refined optimization method. Experiment results show that our method outperforms existing state-of-the-art methods in terms of both accuracy and temporal stability. Visual results and source code are available at: https://pawindergit.github.io/SR-VFA/

In smart cities, face recognition (FR) systems are ubiquitous and they have been extensively used for public safety, traffic management, and other smart services. An FR system usually stores a facial template (i.e., facial feature extracted from face images of enrolled users) dataset and uses it for face recognition. Recent work has shown that FR systems are vulnerable to template inversion (TI) attacks, in which the adversary (who accesses the template dataset) can train a machine learning (ML) model to reconstruct face images from their corresponding templates. However, when only a tiny surrogate dataset is available, these prior learning-based TI attacks fail to achieve good attack performance. To address this issue, we design an Image-Template-Guided GAN (ITGGAN) which can be trained with the guide of face images (in the tiny surrogate dataset) and available templates. ITGGAN can be used to generate a massive number of diversified images, which helps to train a high-quality TI network to launch TI attacks. Additionally, we develop an interactive training strategy where the ITGGAN and the TI network are trained alternately. Applying this strategy, higher diversified images can be used to train the TI network, thereby continuously boosting the attack performance. Our experimental results show that, compared with prior TI attacks, the proposed TI attack achieves the highest ASR (over 99 %) with only 1,000 training samples across four different FR systems and two face datasets.

With the continual advancement of communication technologies, mobile devices have become indispensable tools in our daily lives. While existing sensor-based continuous authentication systems provide some level of user privacy protection, they often neglect the temporal characteristics of multisensor data and the unique information of each sensor. To further protect the privacy of mobile devices, we present FuMeAuth, a sensor-based continuous Authentication system using a Fused Memory-Augmented transformer Autoencoder. FuMeAuth leverages the built-in accelerometer, gyroscope, and magnetometer of smartphones to implicitly gather user behavior patterns. The Fused global–local Memory network (FuMe) effectively captures and adaptively combines the shared-private features of sensor data in FuMeAuth. During the registration phase, FuMeAuth collects and preprocesses the sensor data and sends the processed data to FuMe, which then records fused shared and private representations across different sensors for legitimate users. In the authentication phase, the trained FuMe reconstructs the current user’s data, computes the reconstruction error between user input data and the corresponding reconstructed data, and compares it against a predefined authentication threshold for authentication. We evaluate the performance of FuMeAuth on our data set in terms of the effectiveness of FuMeAuth, effect of sensor numbers, efficiency of fused memory module, and comparison with state-of-the-art approaches. The experimental results demonstrate that FuMeAuth exhibits superior performance than other approaches by achieving an accuracy of 99.84% and an equal error rate of 0.14% with 69 unseen users.

In recent years, sensor-based continuous authentication on mobile devices has proven highly effective in safeguarding personal information. However, these proposed approaches often require the utilization of both legitimate user and imposters’ data for training authentication models, which is time-consuming and ineffective. In this paper, we present AEGANAuth, a lightweight and effective AutoEncoder GAN-based continuous Authentication system for mobile devices using conditional variational AutoEncoder Generative Adversarial Network. AEGANAuth uses a Conditional Variational AutoEncoder Generative Adversarial Network (CVAEGAN) for data augmentation and utilizes an AutoEncoder Generative Adversarial Network (AEGAN) for user data reconstruction. During the enrollment phase, AEGANAuth employs the accelerometer and gyroscope sensors embedded on mobile devices to implicitly collect user behavioral patterns. Using the normalized sensor data, AEGANAuth selects legitimate user data to train CVAEGAN, which consists of a variational encoder, a conditional generator, a discriminator, and a classifier, for AEGAN training data augmentation. Based on the augmented legitimate user data, AEGAN, comprising an encoder, a decoder, and a discriminator, is trained for user data reconstruction. In the authentication phase, when a user operates the mobile device, AEGANAuth collects and normalizes the current user’s data, and then employs the trained AEGAN to reconstruct this user’s data. The reconstruction error is then computed by comparing the reconstructed data to the normalized data. Finally, AEGANAuth with AEGAN compares the reconstruction error to a predetermined authentication threshold for user authentication. We evaluate the performance of AEGANAuth on our dataset, and the experimental results demonstrate an average equal error rate (EER) of 2.13% and an average accuracy of 97.85% on 10 imposters.

Sensor-based continuous authentication mechanisms have demonstrated promising capabilities in enhancing the security of smart devices. In this article, we present SNNAuth, a novel sensor-based continuous Authentication system on smartphones that utilizes Spiking Neural Networks, leveraging biometric behavioral patterns captured by smartphone sensors. To enhance discriminative feature extraction, we introduce positional encoding into the time slicing of normalized sensor data. We design the artificial neural network (ANN)-SNN model, which transforms the trained ANN into an SNN by converting weights and activations into suitable spike neuron models and synaptic connections. The ANN-SNN model, designed for efficient computation and increased robustness, is specifically trained to extract temporal features of a legitimate user. With the extracted features of a legitimate user, we then train the one-class k-nearest neighbors (OC-kNN), which is employed for conducting the classification for all users. Based on the trained ANN-SNN and one-class kNN, SNNAuth determines whether the current user is legitimate or an imposter. Finally, we evaluate the performance of SNNAuth on two public data sets and our data set, and the experimental results demonstrate that SNNAuth outperforms state-of-the-art solutions by achieving the highest accuracy and the lowest equal error rates (EERs) on all three data sets.

The massive amount of data on the Internet of Things (IoT) drives recommendation systems (RSs) based on graph neural network (GNN) to fully play a role in improving user experience. However, data sharing and centralized storage can pose serious security threats. Even though federated learning (FL) can render data “available but not visible,” the heterogeneity of graph data within IoT institutions can result in limitations in recommendation performance. To address the issues, we propose a privacy-preserving decentralized cross-institutional federated graph learning framework called DCI-PFGL for IoT service recommendation, which alleviates the negative impact of data heterogeneity while protecting data security. Our approach extracts graph feature embeddings using the shortest path graph kernel. These embeddings are then anonymized and compared on a blockchain through smart contracts, which helps match partner IoT institutions with lower data heterogeneity. Subsequently, IoT institutions within the same partition collaborate in federated graph learning. We also ensure the protection of transmitted information through differential privacy measures. Finally, we conduct comprehensive experiments on two benchmark data sets. Results demonstrate that DCI-PFGL outperforms other approaches in terms of system accuracy and collaboration costs.

Abstract Facial action units (AUs) encode the activations of facial muscle groups, playing a crucial role in expression analysis and facial animation. However, current deep learning AU detection methods primarily focus on single‐image analysis, which limits the exploitation of rich temporal context for robust outcomes. Moreover, the scale of available datasets remains limited, leading models trained on these datasets to tend to suffer from overfitting issues. This paper proposes a novel AU detection method integrating spatial and temporal data with inter‐subject feature reassignment for accurate and robust AU predictions. Our method first extracts regional features from facial images. Then, to effectively capture both the temporal context and identity‐independent features, we introduce a temporal feature combination and feature reassignment (TC&FR) module, which transforms single‐image features into a cohesive temporal sequence and fuses features across multiple subjects. This transformation encourages the model to utilize identity‐independent features and temporal context, thus ensuring robust prediction outcomes. Experimental results demonstrate the enhancements brought by the proposed modules and the state‐of‐the‐art (SOTA) results achieved by our method.

Internet of Medical Things (IoMT) technologies significantly improve the quality of health care, especially at the time when COVID-19 is becoming a worldwide pandemic. Due to the complexity of devices and user nodes in the IoMT system, there should be some ways to ensure the security and quality of the service or information. Decentralized trust management techniques are efficient means of promoting application security and reliability in these cases. However, the majority of currently utilized access control schemes cannot be applied in decentralized trust management systems or perform poorly owing to the numerous restrictions of decentralized systems. In this article, we present a policy-hiding and multiauthority key generation CP-ABE scheme (PM-CPABE) for decentralized trust management systems, which could provide fine-grained access control capabilities. Meanwhile, the proposed scheme does not require any fully trusted entity, thus it can be well adapted to decentralized trust management systems. The scheme also implements policy hiding to protect user privacy. In addition, it supports large universe and outsourced decryption. The security analyses and performance comparisons give evidence of our scheme is secure and efficient.

Federated learning (FL) is a distributed machine learning (ML) technique that allows numerous Internet of Things (IoT) devices to jointly train an ML model using a centralized server for help. Local data never leaves each IoT device in FL, so the local data of IoT devices are protected. In FL, distributed IoT devices usually collect their local data independently, so the data set of each IoT device may naturally form a distinct source domain. In real-world applications, the model trained over multisource domains may have poor generalization performance on unseen target domains. To address this issue, we propose federated adversarial domain generalization (FedADG) to equip FL with domain generalization capability. FedADG employs the federated adversarial learning approach to measure and align the distributions among different source domains via matching each distribution to a reference distribution. The reference distribution is adaptively generated (by accommodating all source domains) to minimize the domain shift distance during alignment. Therefore, the learned feature representation tends to be universal, and, thus, it has good generalization performance over the unseen target domains while protecting local data privacy. Intensive experiments on various data sets demonstrate that FedADG has comparable performance with the state-of-the-art.

Accurate traffic prediction is a critical yet challenging task in Intelligent Transportation Systems, benefiting a variety of smart services, e.g., route planning and traffic management. Although extensive efforts have been devoted to this problem, it is still not well solved due to the flexible dependency within traffic data along both spatial and temporal dimensions. In this paper, we explore the flexibility from three aspects, namely the time-varying local spatial dependency, the dynamic temporal dependency, and the global spatial dependency. Then we propose a novel Dual Graph Gated Recurrent Neural Network (DG2RNN) to effectively model all these dependencies and offer flexible (multi-step) predictions for future traffic flow. Specifically, we design a Dual Graph Convolution Module to capture the local spatial dependency from two perspectives, namely road distance and adaptive correlation. To model the dynamic temporal dependency, we firstly develop a Bidirectional Gated Recurrent Layer to capture the forward and backward sequential contexts of historical traffic flow, then combine the derived hidden states with their various contributions learned by a temporal attention mechanism. Besides, we further design a spatial attention mechanism to learn the latent global spatial dependency among all locations to facilitate the prediction. Extensive experiments on three types of real-world traffic datasets demonstrate that our model outperforms state-of-the-arts. Results also show our model has more stable performance for the flexible prediction with varying prediction horizons.

The prediction of taxi-passenger’s destination with the partial GPS trajectory left by moving taxis is an important yet challenging research issue. The high uncertainty of human mobility and limited clue provided by the unfinished trajectory are two major barriers to developing effective predictors. In general, such a prediction task is often converted to the identification one among given candidate destinations. Hence, how to extract the discriminative knowledge from the partial trajectory becomes crucial. It is well-recognized that the sequence of visited locations by the taxi has inherent relationship with the heading destination. Inspired by the idea, we propose a novel approach that jointly combines the GPS embedding and attention-based BiLSTM techniques for the prediction of passenger’s destination. Specifically, we propose two GPS embedding methods to encode the geographic proximity and multi-scale spatiality of GPS points into embedding vectors, so as to reveal the spatial context of visited locations in the urban space. After converting GPS trajectories into embedding sequences, we further establish an attention-based dual BiLSTMs neural network to model the relationship between the heading destination and the bidirectional sequential context of visited locations. Meanwhile, the discriminative capability of visited locations in determining the destination can be captured by the attention mechanism. In addition, the OT (origin and time) information is aggregated into the neural network as auxiliary features. Stepping closer to smarter passenger services, rather than telling destinations in terms of drop-off clusters, our proposed model outputs the destinations in terms of historical passengers’ destination clusters. Finally, we evaluate the system performance based on two real large-scale datasets. Results show the superior performance of our proposed model.

In recent years, there have been increasing demands for using deep neural networks (DNNs) to provide image processing services for mobile devices. Considering the privacy of users' images, we utilize a two-tiers DNN which deploys the shallow and deep model on mobile devices and the cloud respectively. Then we propose a novel privacy protection mechanism which is deployed on the mobile device to satisfy the differential privacy. Meanwhile, based on the convolution kernel analysis, we also propose a novel method to improve the computation efficiency of mobile devices. The highlight of our mechanism is that it not only provides customized privacy protection which can resist the attack of Generative Adversarial Network (GAN), but also improves the accuracy of the neural network model. The experimental results on the ImageNet dataset show that we have improved the top-5 accuracy of image classification by 2%-3%. Under the premise of ensuring that the accuracy of the network is not degraded, our method reduces the CPU consumption on the VGG16 and ResNet50 networks to 74.6% and 48.9%, respectively, and can reduce 90% of the memory overhead. This improvement makes it possible to enable mobile deep neural network applications.

Spatial crowdsourcing (SC) is a popular type of crowdsourcing, in which all tasks are associated with locations/regions. Given an SC task, only the participants in the specified location/region are allowed to submit their answers of the task. However, outsourcing the SC tasks to a remote crowdsourcing server poses new security concerns. For example, the task requester may not want to disclose the task content to unauthorized users, and the participants may not want to disclose their locations to untrusted server. To address these issues, we propose a Privacy-Preserving Task Allocation for Spatial Crowdsourcing (PTA-SC) scheme in this paper. In PTASC, regions and locations can be encoded into a set of prefixes based on the prefix encoding method. The location-induced prefixes are treated as attributes and the region-induced prefixes are used to generate an access policy tree for a ciphertext-policy attribute-based encryption (CP-ABE) scheme. PTA-SC can check whether a location is inside an SC task region by evaluating if the attributes satisfy the access policy tree or not. Our theoretical analysis shows that PTA-SC can achieve location privacy preservation and task privacy preservation. Through experiments, we show that PTA-SC scheme can realize adaptive region representation accuracy control and high-efficiency.

Traditional route planners commonly focus on finding the shortest path between two points in terms of travel distance or time over road networks. However, in real cases, especially in the era of smart cities where many kinds of transportation-related data become easily available, recent years have witnessed an increasing demand of route planners that need to optimize for multiple criteria, e.g., finding the route with the highest accumulated scenic score along (utility) while not exceeding the given travel time budget (cost). Such problem can be viewed as a variant of Arc Orienteering Problem (AOP), which is well-known as an NP-hard problem. In this paper, targeting a more realistic AOP, we allow both scenic score (utility) and travel time (cost) values on each arc of the road network are time-dependent (2TD-AOP), and propose a memetic algorithm to solve it. To be more specific, within the given travel time budget, in the phase of initiation, for each population, we iteratively add suitable arcs with high scenic score and build a path from the origin to the destination via a complicate procedure consisting of search region narrowing, chromosome encoding and decoding. In the phase of the local search, each path is improved via local-improvement-based mutation and crossover operations. Finally, we evaluate the proposed memetic algorithm in both synthetic and real-life datasets extensively, and the experimental results demonstrate that it outperforms the baselines.

With the fast development of smart mobile devices, the mobile crowd-sensing (MCS) has been witnessed as a new data collection paradigm. In this paper, we consider a scenario that an MCS server tries to collect trajectories from participants. In order to protect the participants' location privacy from their own side, we let participants submit noisy data to the server. In addition, we assume that the data collection is delay tolerant which means each participant is allowed to submit his trajectory in a bundle instead of submitting locations one by one. Based on this assumption, we regard each trajectory as a vector in the high dimension space and design a trajectory protection algorithm to perturb the true trajectory before submission. We use the differential privacy (DP) as the privacy model so we can estimate the amount of noise given a privacy level. To evaluate our mechanism, we use real world traffic data collected from Shanghai taxis and compare it with existing work. The results show that our mechanism not only guarantees privacy protection, but also preserves trajectories' utility.

As the next generation of information and communication infrastructure, Internet of Things (IoT) enables many advanced applications such as smart healthcare, smart grid, smart home, and so on, which provide the most flexibility and convenience in our daily life. However, pervasive security and privacy issues are also increasing in IoT. For instance, an attacker can get health condition of a patient via analyzing real-time records in a smart healthcare application. Therefore, it is very important for users to protect their private data. In this paper, we present two efficient data aggregation schemes to preserve private data of customers. In the first scheme, each IoT device slices its actual data randomly, keeps one piece to itself, and sends the remaining pieces to other devices which are in the same group via symmetric encryption. Then, each IoT device adds the received pieces and the held piece together to get an immediate result, which is sent to the aggregator after the computation. Moreover, homomorphic encryption and AES encryption are employed to guarantee secure communication. In the second scheme, the slicing strategy is also employed. Noise data are introduced to prevent the exchanged actual data of devices from disclosure when the devices blend data each other. AES encryption is also employed to guarantee secure communication between devices and aggregator, compared to homomorphic encryption, which has significantly less computational cost. Analysis shows that integrity and confidentiality of IoT devices’ data can be guaranteed in our schemes. Both schemes can resist external attack, internal attack, colluding attack, and so on.

Inter-contact time (denoted as TI) between mobile nodes that captures the temporal characteristics of Vehicular Ad Hoc Networks (VANETs) has been intensively studied. Whereas the node spatial distribution is ignored in most existing mobility schemes, which is also worthy of investigation, particularly for real applications. Moreover, the node spatial distribution has a significant influence on the inter-contact time. In this paper, we study the empirical data acquired from taxis in Shanghai city. We find that most taxis distribute on some hot roads which makes the node spatial distribution appear power law. Based on this observation, we propose the concepts of indirect contact and heterogeneous inter-contact time (represented as TH) to reveal how hot roads can change the distribution of inter-contact time. By investigating the empirical data, we show that the THdistribution also appears power law.

Body sensor networks (BSNs) and WiFi networks have been widely investigated due to the availability of sensor motes and WiFi devices, but they are commonly deployed separately. In this paper we propose to optimize the total communication energy consumption of BSN and WiFi (BSN-WiFi) networks using joint data rate adaptation. More specifically, we first elaborate the BSN-WiFi network system in four consecutive phases. Then based on the system, we analyze the communication energy consumption, throughput and time delay, and provide a signal-to-noise ratio and packet delivery ratio (SNR-PDR) mappings of BSN and WiFi networks. Next, we build an energy optimization model with constraints of SNR-PDR mappings, throughput, and time delay to minimize the total communication energy consumption in BSN-WiFi networks. With the input of SNR values, we solve this model by cvx to obtain the output of optimal data rates associated with SNR values, which are then tabulated for online data rate adaptation. Finally, we collect 20-minute traces from a specific BSN-WiFi network system for performance evaluation, and the results demonstrate that our optimal data rate solution achieves up to 86% energy savings comparing with the solutions using fixed data rates.

This paper discusses the challenges in searching imposed by the burgeoning field of Internet of Things (IoT). It first overviews the evolution of the new field to its predecessors: searching in the mobile computing, ubiquitous computing and information retrieve. Then, it identifies four research thrusts: architecture design, search locality, real-time and scalability. It also sketches several presumptive IoT scenarios, and uses them to identify key capabilities missing in today's systems. This paper concludes with a discussion of the research necessary to design and develop these capabilities. In addition, this paper proposes a series of measurement dimensions, based on which it investigates the state-of-the-art efforts.

We consider distributed top-k processing problem in a mobile scenario. Specially, we focus on a real application of a bus network (N nodes), where buses are equipped with cameras for real-time security surveillance. Due to the limited number of screens (k, k<;<;N) at the traffic management center, how to select k bus nodes with most passengers to upload image data by DSRC needs to be solved. We present a novel distributed scheme BSS to handle this so-called "top-k node selection" issue in bus network, in which challenges of low time cost and high accuracy is not trivial. BSS utilizes various strategies to speed up top-k node selection facing poor network condition and application requirements. Performance evaluation is carried out on a real-trace driven simulator, which utilizes about 700 buses in Shanghai. The testing results show that BSS has an excellent performance in terms of time cost and average degree of accuracy, which shows the effectiveness of BSS scheme for real-time security surveillance.

In this paper, we present our study of extracting a mobility model for vehicular ad hoc networks (VANETs) from a large amount of real taxi GPS trace data. In order to capture characteristics of the urban vehicle network from microscopic to macroscopic aspects, we design three parameters and extract their values from the GPS trace data. Using this mobility model, we can generate the synthetic trace to simulate the movement of taxis in the urban area of a metropolis. The validation is carried through extensive comparisons between the synthetic trace and the real trace. Validation results show that our mobility model has a good approximation to the real scenario.

Bus lane enforcement system aims to monitor illegal utilization of bus lane by non-permitted vehicles (violator). However, Road-side system leads to considerable infrastructure cost while bus mounted system has limited surveillance coverage. In this paper, we consider an interesting problem in bus mounted system: how to improve the surveillance coverage of bus mounted system without additional infrastructure cost? In other words, we attempt to identify not only the violator immediately in front of the bus, bus also the violators not close to the bus, whose number plates cannot be read directly because of sight blocking of bus mounted cameras. With utilization of communication between bus and existing cameras around intersections, we propose a novel cooperative violator identification scheme, DoubleChecking, with which violators can be sorted out from traffic flow with high accuracy. From theoretical analysis, DoubleChecking shows a good performance for violator identification, which demonstrates the effectiveness of the proposed scheme.

We consider a practical application of intelligent vehicles for intersection traffic control. Specially, we study the intersection traffic control problem using reservation-based intersection traffic control system, which utilizes the information exchange between intelligent vehicles and management agents around the intersections to direct traffic, instead of traffic lights. We focus on how to design an effective passing permission (PP) allocation strategy for this system. In this work, with an observation that will cause this system to be inefficient, we propose a novel look-ahead passing permission allocation strategy (LICP) for intersection traffic control. The large-scale testing results show that LICP can make nearly 25% performance improvement on average intersection delay than the previous first come, first serve method (FCFS).

Currently, vehicles are equipped with forward facing cameras to assist the forensic investigations of events by proactive image capturing from streets and roads. With content redundancy and storage imbalance in this in-network distributed storage system, how to maximize its storage capacity is a challenge. In other words, how to maximize the average lifetime of sensory data (i.e. images generated by cameras) in network is a fundamental problem need to be solved. This paper presents, VStore, a cooperative storage solution for mobile surveillance in vehicular sensor networks (VSN). The mechanisms in VStore are designed for redundancy elimination by exchanging information between vehicles and storage balancing. Compared with previous work, we deal with new challenges in mobile scenario. Field testing was carried out on a real-trace driven simulator, which utilizes about 500 taxies in Shanghai city. The testing results show that VStore can largely prolong the average lifetime of sensory data by cooperative storage.

Currently, vehicular sensor network (VSN) has been paid much attention for monitoring the physical world of urban areas. We have studied VSNs by utilizing about 4000 taxies and 1000 buses equipped with GPS-based mobile sensors in Shanghai to constitute a virtual vehicular sensor network. The communication-connection intermittence makes the routing issue nontrivial when delay-tolerant applications are deployed in VSNs. The existing DTN routing protocols can be categorized as "neighbor-oriented" and how to select a neighbor candidate was always neglected. In this paper, we present a new DTN routing protocol for Delay-Tolerant Vehicular Sensor Networks, Packet-Oriented Routing protocol (POR), which is designed to emphasize neighbor selection based on awareness of packets to be sent and in consideration of probability to complete transferring of these packets. Our results show that POR performs much better than the ordinary Epidemic routing, as well as other popular routing protocols applied in a similar setting.

The existing vehicular sensors of taxi companies in most of cities can be used for traffic monitoring, however sensors are always set with a long sampling interval because of communication cost saving and network congestion avoidance. In this paper, we focus on the traffic data processing in vehicular sensor networks providing sparse and incomplete information. A performance evaluation study has been carried out in Shanghai by utilizing the sensors installed on 4000 taxis. Two types of traffic status estimation algorithms, the link-based and the vehicle-based, are introduced based on such data basis. The results from large-scale testing cases show that the traffic status can be fairly well estimated based on these imperfect data and we demonstrate the feasibility of such application in most of cities.

We present a mobile sensor system for traffic monitoring (GSSTM), which is a typically Grid application in ShanghaiGrid to provide accurate realtime traffic status information. Several issues and challenges in GSSTM are discussed, such as Grid architecture design, data processing for traffic status estimation, storage strategy of massive data, etc. We implemented a prototype system of GSSTM and carried out a field testing in Shanghai city by using GPS-based sensors on 4000 taxis. The testing results show that by utilizing the Grid technology, the expected performance can be obtained, such as stability, scalability, etc. Meantime, traffic status can be fairly well estimated in GSSTM.

In performance studies of vehicular ad hoc networks (VANETs), the underlying mobility model plays an important role. Since conventional mobile ad hoc network (MANET) routing protocols do not work efficiently in vehicular environments due to the rapid topology changes, the Delay-Tolerant Network (DTN) model is often applied. In this paper, we construct a new mobility model, the Shanghai Urban Vehicular Network (SUVnet) model by using the GPS data from more than 4,000 taxis we have collected, and then investigate the performance of two kinds of DTN routing, the non-geographic pure epidemic routing and our newly-proposed geographic DTN routing, the Distance-Aware Epidemic Routing (DAER). We use the popular random waypoint mobility model and a more complex microscopic traffic simulator generated model for performance comparison. With the two considered DTN routing protocols, conventional mobility models tend to give higher performance results than SUVnet model, the presumably more realistic mobility model.