Industrial time series often display complex, non-stationary behaviors with trends, periodicity, and abrupt fluctuations. Generating high-quality synthetic data in such domains is essential for simulation, forecasting, and anomaly detection in Industrial Internet of Things (IIoT) applications. However, distributional heterogeneity, sparse failure patterns, and long-term dependencies make this task highly challenging. We introduce HNRF-TS, a rectified flow framework with hybrid noise initialization, designed for scalable and robust time series generation. The hybrid prior combines isotropic Gaussian noise with structured codes from a lightweight generative adversarial network (GAN), yielding semantically aligned and diverse latent representations. To improve sampling efficiency, we propose a bimodal adaptive strategy that allocates denser ordinary differential equation (ODE) steps at the beginning and end of the trajectory while using coarser steps in smoother middle regions. This preserves critical temporal features while lowering computational cost. We further enhance fidelity with modules dedicated to modeling trends and seasonality, which capture global drifts and periodic signals inherent in industrial data. Across multiple IIoT datasets, HNRF-TS outperforms state-of-the-art baselines, including GAN-based and diffusion-based methods. It achieves up to 75.8% reduction in Context-FID and over 60% improvement in correlation metrics on long-horizon tasks. Moreover, high-quality samples can be generated with as few as 20 sampling steps, offering significant efficiency gains without sacrificing accuracy.

Due to the growing emphasis on privacy and data governance in machine learning, federated unlearning, an emerging concept in the domain of federated learning, stems from the growing need to address the dynamic nature of data and the evolving requirements related to privacy, compliance, and data management. However, there are some security risks during the unlearning process, including the potential for adversarial manipulation of model integrity, privacy breaches, and performance degradation in a federated learning framework. Although existing research has proposed various defenses to mitigate these risks, significant vulnerabilities remain that can be exploited to undermine the integrity and effectiveness of the unlearning process. Current attack methods are limited by their detectability during training, lack of persistence, and reliance on test-time triggers, which reduces their overall effectiveness. In this paper, we introduce camouflaged poisoning attacks, a novel attack paradigm relevant to federated unlearning. In this approach, some adversary clients initially infuse a small number of meticulously designed points into the dataset, ensuring that the model's predictions are barely influenced. The adversary then makes a request to the exclusion of some of these malicious clients. At this juncture, the attack is activated, leading to a detrimental impact on the model's predictions. The outcomes reveal a substantial potential for these strategies to compromise the effectiveness of models in unlearning scenarios. The essence of this attack involves the creation of deceptive clients that conceal the influence of a contaminated dataset during the federated unlearning process.

Multi-LLM collaborative systems have attracted significant attention as a promising solution for complex tasks, enabling multiple large language models (LLMs) with different domains to work together toward a common goal. Different collaborative structures (e.g., Centralized, Horizontal, and Joint Interaction) and communication methods (e.g., direct, summary, and vote) give the system with enhanced flexibility and reasoning capability. However, these same mechanisms also introduce potential security and privacy risks, such as the generation of incorrect responses and the leakage of sensitive information. Based on the above unique characteristics of collaborative systems, we propose three attack methods (named Decision Poisoning Attack, Indirect Echoleak Attack and Information Collision Attack) that exploit the interactions between LLMs to achieve different objectives like system manipulation and privacy leakage. Extensive experiments demonstrate the effectiveness of the proposed attack on three structures and three communication methods, highlighting the security vulnerabilities and potential risks in Multi-LLM collaborative systems. We further discuss possible defense methods that can mitigate the attack performance. Our work show that (1) the key factor for a successful attack on collaborative systems is ensuring the malicious instruction persists and propagates throughout the inter-LLMs communication. (2) both the system architecture and the communication method can affect attack effectiveness, offering valuable insights for the design of more secure Multi LLM collaborative systems in the future.

Deepfake techniques can now generate multimodal content comprising video and audio tracks. Compared with unimodal Deepfake images, videos or audio, multimodal Deepfake content is more deceptive and easily leads to the dissemination of hate speech, incitement to violence, and disinformation. Therefore, the detection of multimodal Deepfake has attracted much research attention recently. While cross-attention shows the promising capacity for modelling the complicated dependencies between audio and video in multimodal Deepfake detection, it fails to learn accurate cross-modal patterns if audio and video are misaligned in the temporal dimension. Besides, most current multimodal Deepfake detectors only provide a binary classification label, lacking fine-grained localization to identify significant forgery in multiple dimensions (e.g., modal, time, and spatial dimension). In this study, we propose a novel multimodal Deepfake detection framework named ForgeFinder, which goes beyond binary label prediction and achieves multi-grained forgery localization in modal and spatiotemporal dimensions. ForgeFinder incorporates both intra-modal and cross-modal inconsistencies to classify multimodal input. In detail, we adopt Serial Spatiotemporal Self-Attention (SSTSA) in the Intra-Modal Inconsistency Explorer (Intra-MIE), which allows the temporal self-attention to run in the original dimension without bringing unacceptable computational complexity. In the Cross-Modal Inconsistency Explorer (Cross-MIE), we propose the Offset-Shifted Cross-Attention (OSCA) by introducing a time offset term to the conventional cross-attention to mitigate the inaccuracy of cross-modal dependencies modelling brought by the temporal misalignment. By adopting the outputs of Intra-MIE for unimodal tasks, we identify the likelihood of modals being manipulated and localize tampered modals. At the same time, the attention weights of SSTSA can be visualized to pinpoint the temporal and spatial distribution of Deepfake manipulation. Therefore, for a single audio–video input sample, ForgeFinder not only tells the authenticity of the overall input but also localizes the modal, temporal sequence, and spatial coordinates of significant forgery, significantly contributing to more comprehensive forensics analysis. The results of extensive experiments indicate that ForgeFinder achieves state-of-the-art detection performance as well as accurate forgery localization in modal and spatiotemporal dimensions. Furthermore, experiments on content generated by Diffusion Models (DMs) show that our model also effectively recognizes DM-generated content.

Deepfake technology, leveraging advanced artificial intelligence (AI) algorithms, has emerged as a powerful tool for generating hyper‐realistic synthetic human faces, presenting both innovative opportunities and significant challenges. Meanwhile, the development of Deepfake detectors represents another branch of models striving to recognize AI‐generated fake faces and protect people from the misinformation of Deepfake. This ongoing cat‐and‐mouse game between generation and detection has spurred a dynamic evolution in the landscape of Deepfake. This survey comprehensively studies recent advancements in Deepfake generation and detection techniques, focusing particularly on the utilization of generative adversarial networks (GANs) and diffusion models (DMs). For both GAN‐based and DM‐based Deepfake generators, we categorize them based on whether they synthesize new content or manipulate existing content. Correspondingly, we examine various strategies employed to identify synthetic and manipulated Deepfake, respectively. Finally, we summarize our findings by discussing the unique capabilities and limitations of GANs and DM in the context of Deepfake. We also identify promising future directions for research, including the development of hybrid approaches that leverage the strengths of both GANs and DM, the exploration of novel detection strategies utilizing advanced AI techniques, and the ethical considerations surrounding the development of Deepfake. This survey paper serves as a valuable resource for researchers, practitioners, and policymakers seeking to understand the state‐of‐the‐art in Deepfake technology, its implications, and potential avenues for future research and development.

The rapid advancement of Artificial Intelligence (AI) has transformed various industries, leading to the widespread distribution of AI models and data across intelligent systems. As modern data driven services increasingly integrate distributed knowledge entities, decentralized learning has become a prevalent approach to training AI models. However, this collaborative learning paradigm introduces significant security vulnerabilities and privacy challenges. This paper presents a comprehensive systematic review on private knowledge sharing in distributed learning, analyzing key knowledge components utilized in leading distributed learning architectures. We identify critical vulnerabilities associated with these components and examine defensive strategies to safeguard privacy while mitigating potential adversarial threats. Additionally, we highlight key limitations in knowledge sharing in distributed learning and propose future research directions to enhance security and efficiency in decentralized AI systems.

Fairness has emerged as a crucial concern in machine learning since biased models would generate dissimilar predictions for different groups, perpetuating social inequalities. Although numerous techniques have been proposed to address the fairness issue in machine learning, most rely on incorporating fairness constraints during the training phase, rendering them ineffective once the model is deployed. This paper explores the potential of fine-tuning biased models to enhance fairness, particularly suitable for scenarios where retraining the model is not feasible. Our approach is rooted in an empirical analysis of the distribution of bias within a biased model, and we fine-tune the model parameter in a limited scope so that the performance of the original model can be maintained. We first observe that fine-tuning a biased model leads to deviations from its initial state, with deep layers undergoing the most significant changes. We then design and apply a bias-discovery algorithm, revealing that bias predominantly resides in the model’s deep layers. Based on these observations, we propose a straightforward yet highly effective method for debiasing the model: fine-tuning the classification head. We conduct a thorough theoretical analysis to justify the proposed method and provide guidance for fine-tuning. Furthermore, we experimentally validate our method on tabular and image datasets using four networks (CNN, AlexNet, VGG-11, and ResNet-18).

As an increasing number of data-driven deep learning models are deployed in our daily lives, the issue of algorithmic fairness has become a major concern. These models are trained on data that inevitably contains various biases, leading them to learn unfair representations that differ across demographic subgroups, resulting in unfair predictions. Previous work on fairness has attempted to remove subgroup information from learned features, aiming to contribute to similar representations across subgroups and lead to fairer predictions. However, identifying and removing this information is extremely challenging due to the “black box” nature of neural networks. Moreover, removing desired features without affecting other features is difficult, as features are often correlated, potentially harming model prediction performance. This paper aims to learn fair representations without degrading model prediction performance. We adopt knowledge distillation, allowing unfair models to learn fair representations directly from a fair teacher. The proposed method provides a novel approach to obtaining fair representations while maintaining valid prediction performance. We evaluate the proposed method, FairDistill, on four datasets (CIFAR-10, UTKFace, CelebA, and Adult) under diverse settings. Extensive experiments demonstrate the effectiveness and robustness of the proposed method.

While in-processing fairness approaches show promise in mitigating biased predictions, their potential impact on privacy leakage remains under-explored. We aim to address this gap by assessing the privacy risks of fairness-enhanced binary classifiers via membership inference attacks (MIAs) and attribute inference attacks (AIAs). Surprisingly, our results reveal that enhancing fairness does not necessarily lead to privacy compromises. For example, these fairness interventions exhibit increased resilience against MIAs and AIAs. This is because fairness interventions tend to remove sensitive information among extracted features and reduce confidence scores for the majority of training data for fairer predictions. However, during the evaluations, we uncover a potential threat mechanism that exploits prediction discrepancies between fair and biased models, leading to advanced attack results for both MIAs and AIAs. This mechanism reveals potent vulnerabilities of fair models and poses significant privacy risks of current fairness methods. Extensive experiments across multiple datasets, attack methods, and representative fairness approaches confirm our findings and demonstrate the efficacy of the uncovered mechanism. Our study exposes the under-explored privacy threats in fairness studies, advocating for thorough evaluations of potential security vulnerabilities before model deployments.

Model extraction attacks currently pose a non-negligible threat to the security and privacy of deep learning models. By querying the model with a small dataset and using the query results as the ground-truth labels, an adversary can steal a piracy model with performance comparable to the original model. Two key issues that cause the threat are, on the one hand, accurate and unlimited queries can be obtained by the adversary; on the other hand, the adversary can aggregate the query results to train the model step by step. The existing defenses usually employ model watermarking or fingerprinting to protect the ownership. However, these methods cannot proactively prevent the violation from happening. To mitigate the threat, we propose QUEEN (QUEry unlEarNing) that proactively launches counterattacks on potential model extraction attacks from the very beginning. To limit the potential threat, QUEEN has sensitivity measurement and outputs perturbation that prevents the adversary from training a piracy model with high performance. In sensitivity measurement, QUEEN measures the single query sensitivity by its distance from the center of its cluster in the feature space. To reduce the learning accuracy of attacks, for the highly sensitive query batch, QUEEN applies query unlearning, which is implemented by gradient reverse to perturb the softmax output such that the piracy model will generate reverse gradients to worsen its performance unconsciously. Experiments show that QUEEN outperforms the state-of-the-art defenses against various model extraction attacks with a relatively low cost to the model accuracy. The artifact is publicly available athttps://github.com/MaraPapMann/QUEEN.

Authentication is an important security issue for multi-access edge computing (MEC). To restrict user access from untrusted devices, Bring Your Own Device (BYOD) policy has been proposed to authenticate users and devices simultaneously. However, when integrating BYOD policy into MEC authentication to improve security, issues of efficient binding and user-device conditional anonymity have not been well supported. To address these issues, we propose Bring Your Device Group (BYDG) policy by constructing efficient and privacy-preserving user-device authentication. Our core idea is to use key sequences generated by PUFs-based key derivation functions (KDFs) to not only construct efficient binding relationships, but also achieve conditional anonymity for device groups. Specifically, a flexible and secure binding method is first developed by leveraging Chinese Remainder Theorem (CRT) to bind user with device groups. Each device’s CRT modulus is derived from the key sequence to construct many-to-many user-device binding relationships, which are managed in the form of on-chain Pedersen Commitment. Moreover, we design an identity anonymizing and tracing method for device groups. The key sequence is regarded as traceable device pseudo-identities, and then inserted into the cuckoo filter to reduce the on-chain storage overhead and mitigate malicious login attempts with low costs. Based on above two methods, the combination of Pedersen Commitment and Zero-Knowledge Proof of Knowledge is used to achieve user-device authentication with conditional anonymity. The security analysis was presented to demonstrate important security properties. A proof-of-concept prototype was implemented to conduct performance evaluation and comparative analysis.

While existing fairness interventions show promise in mitigating biased predictions, most studies concentrate on single-attribute protections. Although a few methods consider multiple attributes, they either require additional constraints or prediction heads, incurring high computational overhead or jeopardizing the stability of the training process. More critically, they consider per-attribute protection approaches, raising concerns about fairness gerrymandering where certain attribute combinations remain unfair. This work aims to construct a neutral domain containing fused information across all subgroups and attributes. It delivers fair predictions as the fused input contains neutralized information for all considered attributes. Specifically, we adopt mixup operations to generate samples with fused information. However, our experiments reveal that directly adopting the operations leads to degraded prediction results. The excessive mixup operations result in unrecognizable training data. To this end, we design three distinct mixup schemes that balance information fusion across attributes while retaining distinct visual features critical for training valid models. Extensive experiments with multiple datasets and up to eight sensitive attributes demonstrate that the proposed MultiFair method can deliver fairness protections for multiple attributes while maintaining valid prediction results.

The rise of Deepfake technology has sparked significant concerns due to its potential for misuse and malicious manipulation of multimedia content. Various detection approaches aimed at detecting Deepfake videos have been proposed, mostly relying on the identification of spatial and temporal artifacts. However, due to the different contexts of source images and the variety of generation techniques, current Deepfake detection methods usually perform well on training datasets, and yet generalize poorly to those unseen identities in new datasets. This issue is widely known as the generalization challenge of Deepfake detection. To address this challenge, this paper proposes an advanced spatiotemporal Deepfake video detector, named M otion- e nhanced S patiotemporal T ransformer (MeST-Former). MeST-Former is based on the spatiotemporal modeling capacity of the video Swin Transformer. The spatial and temporal features are obtained from the RGB and motion images, respectively. To enhance the generalization ability of MeST-Former to unseen identities in unseen datasets, the ID-related components in the spatial and temporal features are detached. Specifically, MeST-Former adopts the newly proposed Identity-Decoupling Attention (IDC-Att) module to disentangle the ID-related and ID-unrelated components. Only the ID-unrelated components are used to construct more generalizable spatiotemporal representations. This process makes the constructed spatiotemporal features identity-agnostic and more generalizable to unseen identities. We conducted extensive experiments to evaluate the performance of the MeST-Former. Our results indicate that MeST-Former achieves accurate and generalizable Deepfake detection performance. Notably, MeST-Former also demonstrates high efficacy in detecting AI-animated talking-head videos. • RGB and motion inputs provide distinctive spatial and temporal information. • Detaching ID-related components from original embeddings can improve the generalization capabilities of the Deepfake detector. • The Swin Transformer are powerful in modeling spatiotemporal embeddings for classification. • An effectively implemented face-cropping strategy minimizes the influence of background elements.

Malicious image tampering refers to intentionally manipulating images to make them harmful to the owners or users. It has become one of the most severe challenges to image authenticity. Conventional methods for detecting tampering by identifying visual artifacts and distortions have limitations due to the rapid advancement of image manipulation techniques, which leave fewer detectable traces. To address these challenges, we propose a proactive media authentication method using deep learning-based semi-fragile watermarks. The designed scheme utilizes deep neural networks to embed an invisible watermark into a target image that is pixel-by-pixel entangled with it, which acts as an indicator of tampering trails. Once the watermarked image is counterfeited, the embedded watermark will exhibit changes accordingly, so we can locate the tampered regions by comparing retrieved and original watermarks. This proactive authentication mechanism makes our method effective against various image tamper techniques, including image copy&move, splicing and in-painting. Although our watermark is designed to be fragile to malicious tampering operations, it remains robust to benign image-processing operations such as JPEG compression, scaling, saturation, contrast adjustments, etc. This design enables our watermark to retain effectiveness when shared over the internet. Extensive experiments demonstrate that our method achieves state-of-the-art forgery detection with superior robustness, imperceptibility and security performance.

Physically Unclonable Functions (PUFs) have emerged as hardware fingerprints for IoT devices in the form of challenge-response pairs (CRPs). This mapping behaviour is regarded as a physically secure primitive, activating mechanisms of authentication and data protection. However, multidimensional security threats to CRPs, including impersonation attacks, availability attacks, machine learning attacks, and single point failure, impede the applications of PUFs technology. To simultaneously solve these threats, this paper not only leverages Shamir secret sharing (SSS) to provide comprehensive CRPs protection, but also integrates blockchain to address trust issues of synchronization, supervision, and deployment brought by the SSS system. Specifically, we first propose a security-enhanced and reliable CRPs management method. This method leverages SSS and its homomorphic addition feature to protect CRPs storage, sharing, and backup processes. Meanwhile, blockchain is involved in the SSS system to synchronize CRPs and supervise sharing behaviours. Then, a PUF-as-a-service (PaaS) framework is constructed, which utilizes blockchain to trace the change of the SSS system and integrate different PUFs-based security mechanisms. Once deployed in PaaS, users can always utilize transactions to build secure on-chain channels with SSS system and employ the PUF service. Based on our CRPs management method and PaaS framework, we successfully constructed PUFs-based distributed authentication and recoverable data sharing with multidimensional CRPs protection. The security proof and discussions of our scheme are also provided. Moreover, a proof-of-concept prototype was implemented to conduct experimental evaluations and comparative analysis. The results and additional discussions demonstrate that our work is efficient, practical, and suitable for IoT deployment.

Federated learning is a distributed learning paradigm where a global model is trained using data samples from multiple clients but without the necessity of sharing raw data samples. However, it comes with several significant challenges in system designs, data quality, and communications. Recent research highlights a significant concern related to data privacy leakage through reserve-engineering model gradients at a malicious server. Moreover, a global model cannot provide good utility performance for individual clients when the local training data is heterogeneous in terms of quantity, quality, and distribution. Hence, personalized federated learning is highly desirable in practice to tailor the trained model for local usage. In this paper, we propose PPFed, a unified federated learning framework to simultaneously address privacy preservation and personalization. The intuition of our framework is to learn part of the model gradients at the server and the rest of the gradients at the local clients. To evaluate the effectiveness of the proposed framework, we conduct extensive experiments across four image classification datasets to show that our framework yields better privacy and personalization performance compared to the existing methods. We also claim that privacy preservation and personalization are essentially two facets of deep learning models, offering a unique perspective on their intrinsic interrelation.

Face de-identification involves concealing the true identity of a face while retaining other facial characteristics. Current target-generic methods typically disentangle identity features in the latent space, using adversarial training to balance privacy and utility. However, this pattern often leads to a trade-off between privacy and utility, and the latent space remains difficult to explain. To address these issues, we propose IDeudemon, which employs a "divide and conquer" strategy to protect identity and preserve utility step by step while maintaining good explainability. In Step I, we obfuscate the 3D disentangled ID code calculated by a parametric NeRF model to protect identity. In Step II, we incorporate visual similarity assistance and train a GAN with adjusted losses to preserve image utility. Thanks to the powerful 3D prior and delicate generative designs, our approach could protect the identity naturally, produce high quality details and is robust to different poses and expressions. Extensive experiments demonstrate that the proposed IDeudemon outperforms previous state-of-the-art methods.

The widespread application of face recognition technology has exacerbated privacy threats. Face de-identification is an effective means of protecting visual privacy by concealing identity information. While deep learning-based methods have greatly improved de-identification results, most existing algorithms rely on 2D generative models that struggle to produce identity-consistent results for multiple views. In this paper, we focus on identity disentanglement within the latest 3D-aware face generation model, and propose an advanced face de-identification framework that can be applied to various scenarios. Our proposed framework disentangles identity from other facial features, modifies only the former and generates the de-identified face using a 3D generator. This approach results in high-quality, identity-consistent de-identification that preserves other facial features. We demonstrate our approach on StyleNeRF, one of the most widely-used style-based neural radiation field models. Through extensive experiments, we demonstrate the effectiveness of our approach in achieving face de-identification both for a single image and group images with the same identity. Our work is a significant step forward in the field of face de-identification, opening up new possibilities for practical applications.

In this paper, we propose the Temporal Identity Inconsistency Network (TI2Net), a Deepfake detector that focuses on temporal identity inconsistency. Specifically, TI2Net recognizes fake videos by capturing the dissimilarities of human faces among video frames of the same identity. Therefore, TI2Net is a reference-agnostic detector and can be used on unseen datasets. For a video clip of a given identity, identity information in all frames will first be encoded to identity vectors. TI2Net learns the temporal identity embedding from the temporal difference of the identity vectors. The temporal embedding, representing the identity inconsistency in the video clip, is finally used to determine the authenticity of the video clip. During training, TI2Net incorporates triplet loss to learn more discriminative temporal embeddings. We conduct comprehensive experiments to evaluate the performance of the proposed TI2Net. Experimental results indicate that TI2Net generalizes well to unseen manipulations and datasets with unseen identities. Besides, TI2Net also shows robust performance against compression and additive noise.

The explosive progress of Deepfake techniques poses unprecedented privacy and security risks to our society by creating real-looking but fake visual content. The current Deepfake detection studies are still in their infancy because they mainly rely on capturing artifacts left by a Deepfake synthesis process as detection clues, which can be easily removed by various distortions (e.g. blurring) or advanced Deepfake techniques. In this paper, we propose a novel method that does not depend on identifying the artifacts but resorts to the mechanism of anti-counterfeit labels to protect face images from malicious Deepfake tampering. Specifically, we design a neural network with an encoder-decoder structure to embed watermarks as anti-Deepfake labels into the facial identity features. The injected label is entangled with the facial identity feature, so it will be sensitive to face swap translations (i.e., Deepfake) and robust to conventional image modifications (e.g., resize and compress). Therefore, we can identify whether watermarked images have been tampered with by Deepfake methods according to the label’s existence. Experimental results demonstrate that our method can achieve average detection accuracy of more than 80%, which validates the proposed method’s effectiveness in implementing Deepfake detection.

Summary Privacy leakage in images attracts increasing concerns these days, as photos uploaded to large social platforms are usually not processed by proper privacy protection mechanisms. Moreover, with advanced artificial intelligence (AI) tools such as deep neural network (DNN), an adversary can detect people's identities and collect other sensitive personal information from images at an unprecedented scale. In this paper, we introduce a novel face image de‐identification framework using adversarial perturbations in the feature space. Manipulating the feature space vector ensures the good transferability of our framework. Moreover, the proposed feature space adversarial perturbation generation algorithm can successfully protect the identity‐related information while ensuring the other attributes remain similar. Finally, we conduct extensive experiments on two face image datasets to evaluate the performance of the proposed method. Our results show that the proposed method can generate real‐looking privacy‐preserving images efficiently. Although our framework has only been tested on two real‐life face image datasets, it can be easily extended to other types of images.

Small unmanned air vehicles (UAVs) have many advantages, including low cost and flexible deployment. And they play an important role to collect the sensing data of Internet of Things (IoT). However, limited by the load capability, it is a big challenge for them to perform long-term, large range, or far distance tasks. In order to tackle these challenges, we propose to use assembly UAVs, in which we can jointly optimize the resource management, especially, the energy resource. The system model, energy cyclic cooperation, and one of the typical applications based on assembly UAVs are introduced. The energy cooperation problems are formulated and an in-air replenishing strategy (IA-RS) is proposed. Simulations show that the performances of the proposed IA-RS outperform those of the traditional on-ground replenishing strategy (OG-RS). The working time of task UAV (UAV-T) could reduce 8.3%–19.5%, and the freshness of the collected data and the collecting efficiency of the UAV-T can be improved. We also optimize the path of the replenishing UAVs (UAV-Rs). Simulations show that the proposed reinforcement learning (RL) algorithm has the best performances and acceptable complexity. Consequently, the efficiency of the IoT data collection task is improved by the proposed assembly UAVs.

Motivated by the advancing computational capacity of distributed end-user equipment (UE), as well as the increasing concerns about sharing private data, there has been considerable recent interest in machine learning (ML) and artificial intelligence (AI) that can be processed on distributed UEs. Specifically, in this paradigm, parts of an ML process are outsourced to multiple distributed UEs. Then, the processed information is aggregated on a certain level at a central server, which turns a centralized ML process into a distributed one and brings about significant benefits. However, this new distributed ML paradigm raises new risks in terms of privacy and security issues. In this article, we provide a survey of the emerging security and privacy risks of distributed ML from a unique perspective of information exchange levels, which are defined according to the key steps of an ML process, i.e., we consider the following levels: 1) the level of preprocessed data; 2) the level of learning models; 3) the level of extracted knowledge; and 4) the level of intermediate results. We explore and analyze the potential of threats for each information exchange level based on an overview of current state-of-the-art attack mechanisms and then discuss the possible defense methods against such threats. Finally, we complete the survey by providing an outlook on the challenges and possible directions for future research in this critical area.

Generative adversarial networks (GANs) have attracted increasing attention recently owing to their impressive abilities to generate realistic samples with high privacy protection. Without directly interacting with training examples, the generative model can be used to estimate the underlying distribution of an original dataset while the discriminator can examine model quality of the generated samples by comparing the label values with training examples. In considering privacy issues in GANS, existing works focus on perturbing the parameters and analyzing the corresponding privacy protection capability, and the parameters are not directly exchanged between the generator and discriminator in GANs. Thus, in this work, we propose a Rényi-differentially private-GAN (RDP-GAN), which achieves differential privacy (DP) in a GAN by carefully adding random Gaussian noise to the value of the exchanged loss function during training. Moreover, we derive analytical results characterizing the total privacy loss under the subsampling method and cumulative iterations, which show its effectiveness for the privacy budget allocation. In addition, in order to mitigate the negative impact of injecting noises, we enhance the proposed algorithm by adding an adaptive noise tuning step, which will change the amount of added noise according to the testing accuracy. Through extensive experimental results, we verify that the proposed algorithm can achieve a better privacy level while producing high-quality samples compared with a benchmark DP-GAN scheme based on noise perturbation on training gradients.

Recent research has discovered that deep learning models are vulnerable to membership inference attacks, which can reveal whether a sample is in the training dataset of the victim model or not. Most membership inference attacks rely on confidence scores from the victim model for the attack purpose. However, a few studies indicate that prediction labels of the victim model's output are sufficient for launching successful attacks. Besides the well-studied classification models, segmentation models are also vulnerable to this type of attack. In this article, for the first time, we propose the label-only membership inference attacks against semantic segmentation models. With a well-designed framework of the attacks, we can achieve a considerably higher successful attacking rate compared to previous work. In addition, we have discussed several possible defense mechanisms to counter such a threat.

In a model inversion attack, an adversary attempts to reconstruct the training data records of a target model using only the model’s output. In launching a contemporary model inversion attack, the strategies discussed are generally based on either predicted confidence score vectors, i.e., black-box attacks, or the parameters of a target model, i.e., white-box attacks. However, in the real world, model owners usually only give out the predicted labels; the confidence score vectors and model parameters are hidden as a defense mechanism to prevent such attacks. Unfortunately, we have found a model inversion method that can reconstruct representative samples of the target model’s training data based only on the output labels. We believe this attack requires the least information to succeed and, therefore, has the best applicability. The key idea is to exploit the error rate of the target model to compute the median distance from a set of data records to the decision boundary of the target model. The distance is then used to generate confidence score vectors which are adopted to train an attack model to reconstruct the representative samples. The experimental results show that highly recognizable representative samples can be reconstructed with far less information than existing methods.

Summary The explosive growth of various computer vision technologies generates a tremendous amount of visual data online every day. In addition to bringing convenience and revolutionizing our daily life, image data also reveal a wide range of sensitive information and pose unprecedented privacy leakage risks. Particularly, in the case of photos contain human faces, people can easily access those face images on social media without any consent, and the misuse of personal information could cause serious privacy violation to individuals. Therefore, it is essential to consider sanitizing people's identity information when using images containing human faces. As a result, there has been rapid development in the area of facial anonymization, also called image de‐identification. However, due to the emergence of numerous deep‐learning based attacks, traditional anonymization methods such as blurring and mosaic are weak and ineffective to protect individual's privacy in face images. To respond to this challenge, this article proposes a novel de‐identification method that utilizes a deep neural network. The proposed framework encompasses two modules: encoder network and generator network. The encoder transforms a face image into a high‐semantic latent vector of codes, which will be de‐identified according to the differential privacy criterion. The generator leverages the unconditional generative adversarial network to synthesize high‐quality images based on the modified latent codes from the encoder. Extensive experimental results indicate that our proposed model can protect image privacy while keeping the processed image visual realistic.

Federated Learning (FL), as a privacy-preserving machine learning paradigm, has been thrusted into the limelight. As a result of the physical bandwidth constraint, only a small number of clients are selected for each round of FL training. However, existing client selection solutions (e.g., the vanilla random selection) typically ignore the heterogeneous data value of the clients. In this paper, we propose the contribution-based selection algorithm (Contribution-Based Exponential-weight algorithm for Exploration and Exploitation, CBE3), which dynamically updates the selection weights according to the impact of clients' data. As a novel component of CBE3, a scaling factor, which helps maintain a good balance between global model accuracy and convergence speed, is proposed to improve the algorithm's adaptability. Theoretically, we proved the regret bound of the proposed CBE3 algorithm, which demonstrates performance gaps between the CBE3 and the optimal choice. Empirically, extensive experiments conducted on Non-Independent Identically Distributed data demonstrate the superior performance of CBE3—with up to 10% accuracy improvement compared with K-Center and Greedy and up to 100% faster convergence compared with the Random algorithm.

Industrial Internet of Things (IIoT) has emerged as a prospective technology that improves the productivity and automation level for industrial applications. Devices from cooperative IIoT domains will communicate and collaborate on the increasingly complicated manufacturing tasks. To secure cross-domain device collaborations, we propose combining the blockchain with multifactor authentication. Because the multifactor authentication conforms to IIoT devices’ operation modes and brings higher security levels, and the blockchain technology contributes to building trust among different domains. However, this combined usage still has limitations in terms of the potential loss of factor attack, the storage overhead on the blockchain, and the contradiction between efficiency and privacy preservation. Motivated by these facts, in this article, we develop a privacy-preserving blockchain-based multifactor device authentication protocol for cross-domain IIoT. Specifically, multiple factors are additionally encoded by the hardware fingerprint into random numbers, before being transformed into key materials. The blockchain only stores each domain’s dynamic accumulator, which accumulates derived key materials for devices, thereby reducing the overhead. Moreover, the on-chain accumulator is leveraged to efficiently verify the unlinkable identities of cross-domain IIoT devices. The security of our protocol is formally proved, and the security features and functionalities are, respectively, discussed. A proof-of-concept prototype was implemented to prove the efficiency and reliability. The comparison results indicate that the on-chain storage is greatly reduced. Finally, the smart contract’s performance was evaluated to show scalability.

Unprecedented video collection and sharing have exacerbated privacy concerns and led to increasing interest in privacy-preserving tools. A satisfactory video de-identification tool should be able to remove sensitive identity information from face videos while maintaining useful information for other identity-agnostic tasks. Meanwhile, it is necessary to allow the authority to inspect real identity when abnormal events are detected. Existing methods only focus on the study of de-identification, and lack the desired recovery ability when granting permissions. Furthermore, they all process the videos frame by frame, which hardly benefit from motion and inter-frame information. In this paper, we propose a modular architecture for reversible face video de-identification, called IdentityMask, which leverages deep motion flow to avoid per-frame evaluation. Our framework consists of two processes: the de-identification process provides a protective mask for identity information, while the recovery process can remove the protective mask if and only if the right key is provided. To this end, a Protection Module and a Recovery Module are built as two major functional modules, both based on an identity disentanglement network and guided by a crucial Motion Flow Module. An Affine Transformation Module provides simple but reliable assistance. Extensive experiments on a diverse natural video dataset (gender, ethnicity, age, etc.) demonstrate the effectiveness of the proposed framework for reversible face video de-identification.

Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record’s membership in a dataset or even reconstruct this data record using a confidence score vector predicted by the target model. However, most existing defense methods only protect against membership inference attacks. Methods that can combat both types of attacks require a new model to be trained, which may not be time-efficient. In this paper, we propose a differentially private defense method that handles both types of attacks in a time-efficient manner by tuning only one parameter, the privacy budget. The central idea is to modify and normalize the confidence score vectors with a differential privacy mechanism which preserves privacy and obscures membership and reconstructed data. Moreover, this method can guarantee the order of scores in the vector to avoid any loss in classification accuracy. The experimental results show the method to be an effective and timely defense against both membership inference and model inversion attacks with no reduction in accuracy.

The popularization of intelligent devices including smartphones and surveillance cameras results in more serious privacy issues. De-identification is regarded as an effective tool for visual privacy protection with the process of concealing or replacing identity information. Most of the existing de-identification methods suffer from some limitations since they mainly focus on the protection process and are usually non-reversible. In this paper, we propose a personalized and invertible de-identification method based on the deep generative model, where the main idea is introducing a user-specific password and an adjustable parameter to control the direction and degree of identity variation. Extensive experiments demonstrate the effectiveness and generalization of our proposed framework for both face de-identification and recovery.

Advances in cameras and web technology have made it easy to capture and share large amounts of face videos over to an unknown audience with uncontrollable purposes. These raise increasing concerns about unwanted identity-relevant computer vision devices invading the characters's privacy. Previous de-identification methods rely on designing novel neural networks and processing face videos frame by frame, which ignore the data feature in redundancy and continuity. Besides, these techniques are incapable of well-balancing privacy and utility, and per-frame evaluation is easy to cause flicker. In this paper, we present deep motion flow, which can create remarkable de-identified face videos with a good privacy-utility tradeoff. It calculates the relative dense motion flow between every two adjacent original frames and runs the high quality image anonymization only on the first frame. The de-identified video will be obtained based on the anonymous first frame via the relative dense motion flow. Extensive experiments demonstrate the effectiveness of our proposed de-identification method.

The combination of the Internet of Things (IoT) and cloud-edge (CE) paradigm promises to be an efficient system to aggregate and further process huge volumes of data from IoT nodes. Physical unclonable functions (PUFs) emerge as a prospective primitive to provide IoT nodes with lightweight physical identities for authentication. However, when integrating PUFs into multiserver authentication protocols to improve security, the following problems occur: 1) the challenge–response pairs (CRPs) of PUFs generated by devices need to be explicitly stored by each edge server. This will cause the privacy leakage of CRPs; 2) the reliability is reduced resulting from the single point failure; and 3) existing PUFs-based authentication protocols would need to put great efforts into synchronizing CRPs, to ensure consistency in multiserver systems. To overcome these problems, in this article, we propose a privacy-aware authentication protocol for the multiserver CE-IoT systems by combining PUFs and the blockchain technique. The real correlations of CRPs are double encoded into mapping correlations (MCs) by a one-time physical identity and the keyed-hash function. The blockchain is leveraged to store MCs, synchronize them efficiently, and incorporate the multireceiver encryption to share the physical identity securely. The security of our protocol is formally proved by a random oracle model, and security features are discussed to show that our protocol resists various attacks. Moreover, a prototype was implemented to prove the efficiency of the protocol, and the comparison results present that our protocol accommodates CE-IoT systems. Finally, the simulation of the smart contract evaluates the scalability of our protocol.

Publishing datasets plays an essential role in open data research and promoting transparency of government agencies. However, such data publication might reveal users' private information. One of the most sensitive sources of data is spatiotemporal trajectory datasets. Unfortunately, merely removing unique identifiers cannot preserve the privacy of users. Adversaries may know parts of the trajectories or be able to link the published dataset to other sources for the purpose of user identification. Therefore, it is crucial to apply privacy preserving techniques before the publication of spatiotemporal trajectory datasets. In this paper, we propose a robust framework for the anonymization of spatiotemporal trajectory datasets termed as machine learning based anonymization (MLA). By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use k-means algorithm for this purpose. A variation of k-means algorithm is also proposed to preserve the privacy in overly sensitive datasets. Moreover, we improve the alignment process by considering multiple sequence alignment as part of the MLA. The framework and all the proposed algorithms are applied to T-Drive, Geolife, and Gowalla location datasets. The experimental results indicate a significantly higher utility of datasets by anonymization based on MLA framework.

Recent years have seen rising needs for location-based services in our everyday life. Aside from the many advantages provided by these services, they have caused serious concerns regarding the location privacy of users. Adversaries can monitor the queried locations by users to infer sensitive information, such as home addresses and shopping habits. To address this issue, dummy-based algorithms have been developed to increase the anonymity of users, and thus, protecting their privacy. Unfortunately, the existing algorithms only assume a limited amount of side information known by adversaries, which may face more severe challenges in practice. In this paper, we develop an attack model termed as Viterbi attack, which represents a realistic privacy threat on user trajectories. Moreover, we propose a metric called transition entropy that enables the evaluation of dummy-based algorithms, followed by developing a robust algorithm that can defend users against the Viterbi attack while maintaining significantly high performance in terms of the traditional metrics. We compare and evaluate our proposed algorithm and metric on a publicly available dataset published by Microsoft, i.e., Geolife dataset.

Privacy protection attracts increasing concerns these days. People tend to believe that large social platforms will comply with the agreement to protect their privacy. However, photos uploaded by people are usually not treated to achieve privacy protection. For example, Facebook, the world's largest social platform, was found leaking photos of millions of users to commercial organizations for big data analytics. A common analytical tool used by these commercial organizations is the Deep Neural Network (DNN). Today's DNN can accurately identify people's appearance, body shape, hobbies and even more sensitive personal information, such as addresses, phone numbers, emails, bank cards and so on. To enable people to enjoy sharing photos without worrying about their privacy, we propose an algorithm that allows users to selectively protect their privacy while preserving the contextual information contained in images. The results show that the proposed algorithm can select and perturb private objects to be protected among multiple optional objects so that the DNN can only identify non-private objects in images.

As more and more personal photos are shared and tagged in social media, security and privacy protection are becoming an unprecedentedly focus of attention. Avoiding privacy risks such as unintended verification, becomes increasingly challenging. To enable people to enjoy uploading photos without having to consider these privacy concerns, it is crucial to study techniques that allow individuals to limit the identity information leaked in visual data. In this paper, we propose a novel hybrid model consists of two stages to generate visually pleasing de-identified face images according to a single input. Meanwhile, we successfully preserve visual similarity with the original face to retain data usability. Our approach combines latest advances in GAN-based face generation with well-designed adjustable randomness. In our experiments we show visually pleasing de-identified output of our method while preserving a high similarity to the original image content. Moreover, our method adapts well to the verificator of unknown structure, which further improves the practical value in our real life.

The location privacy issue has become a critical research topic recently. The existing solutions do not solve one typical problem in practice: people may only want to protect certain privacy-sensitive locations among a group of temporal and spatial correlated points in a trajectory. As an effort towards this issue, we analyze the impact of space-time relationship on location privacy preservation. In addition, we propose new privacy definitions to better evaluate the privacy level and prove that the target location's privacy can be enhanced by randomizing its time and space related points. Moreover, under the constraint of the total noise power, the problem of obfuscating a location in a temporal and spatial correlated trajectory is formulated as finding the best noise allocation vector which can achieve the highest privacy level. This problem is solved by our proposed location privacy preserving method which applies differential privacy scheme on a series of points with noise budget allocation. Lastly, the performance of the proposed scheme is evaluated by simulations.

Image retargeting is the technique to display images via devices with various aspect ratios and sizes. Traditional content-aware retargeting methods rely on low-level features to predict pixel-wise importance and can hardly preserve both the structure lines and salient regions of the source image. To address this problem, we propose a novel adaptive image warping approach which integrates with deep convolutional neural network. In the proposed method, a visual importance map and a foreground mask map are generated by a pre-trained network. The two maps and other constraints guide the warping process to yield retargeted results with less distortions. Extensive experiments in terms of visual quality and a user study are carried out on the widely used RetargetMe dataset. Experimental results show that our method outperforms current state-of-art image retargeting methods.

Summary Deep learning methods have become the basis of new AI‐based services on the Internet in big data era because of their unprecedented accuracy. Meanwhile, it raises obvious privacy issues. The deep learning–assisted privacy attack can extract sensitive personal information not only from the text but also from unstructured data such as images and videos. In this paper, we proposed a framework to protect image privacy against deep learning tools, along with two new metrics that measure image privacy. Moreover, we propose two different image privacy protection schemes based on the two metrics, utilizing the adversarial example idea. The performance of our solution is validated by simulations on two different datasets. Our research shows that we can protect the image privacy by adding a small amount of noise that has a humanly imperceptible impact on the image quality, especially for images of complex structures and textures.

The unprecedented accuracy of deep learning methods has earned themselves as the foundation of new AI-based services on the Internet. At the same time, it presents obvious privacy issues. The deep learning aided privacy attack can dig out sensitive personal information not only from the text but also from unstructured data such as images and videos. In this paper, we proposed a framework to protect image privacy against the deep learning tools. We also propose two new metrics to measure the image privacy. Moreover, we propose two different image privacy protection schemes based on the two metrics, utilizing the adversarial example idea. The performance of our schemes is validated by simulation on a large-scale dataset. Our study shows that we can protect the image privacy by adding a small amount of noise, while the added noise has a humanly imperceptible impact on the image quality.

In the age of big data, the services in pervasive edge environment are expected to offer end-users better Quality of Experience (QoE) than that in a normal edge environment. Nevertheless, various types of edge devices with storage, delivery, and sensing are coming into our environment and produce the high-dimensional big data accompanied by a volume of pervasive big data increasingly with a lot of redundancy. Therefore, the satisfaction of QoE becomes the primary challenge in high dimensional big data on the basis of pervasive edge environment. In this paper, we first propose a QoE model to evaluate the quality of service in pervasive edge environment. The value of QoE does not only include the accurate data, but also the transmission rate. Then, on the basis of the accuracy, we propose a Tensor-Fast Convolutional Neural Network (TF-CNN) algorithm based on Deep Learning, which is suitable for pervasive edge environment with high-dimensional big data analysis. Simulation results reveal that our proposals could achieve high QoE performance.

Internet of Multimedia Things (IoMT) faces the challenge of how to realize low-cost data acquisition while still preserve data confidentiality. In this paper, we present a low-cost and confidentiality-preserving data acquisition framework for IoMT. First, we harness chaotic convolution and random subsampling to capture multiple image signals. The measurement matrix is under the control of chaos, ensuring the security of the sampling process. Next, we assemble these sampled images into a big master image, and then encrypt this master image based on Arnold transform and single value diffusion. The computation of these two transforms only requires some low-complexity operations. Finally, the encrypted image is delivered to cloud servers for storage and decryption service. Experimental results demonstrate the security and effectiveness of the proposed framework.

Copyright protection of audio data is a serious problem and spread spectrum (SS) based audio watermarking is a promising technology to tackle this problem. Although a number of SS-based audio watermarking methods have been reported in the literature, they cannot achieve high robustness and embedding capacity at the same time. In this paper, we propose a novel SS-based audio watermarking method that can embed a large number of watermark bits into an audio signal without compromising the robustness against common attacks. Compared with the existing audio watermarking methods, the proposed one is especially robust against severe noise addition and compression attacks, while achieving high embedding capacity. Moreover, the new audio watermarking method is computationally efficient. The validity of the proposed SS-based audio watermarking method is demonstrated by simulation results.

Accurate malware propagation modeling in wireless ad hoc networks (WANETs) represents a fundamental and open research issue which shows distinguished challenges due to complicated access competition, severe channel interference, and dynamic connectivity. As an effort towards the issue, in this paper, we investigate the malware propagation under two spread schemes including Unicast and Broadcast, in Spread Mode and Communication Mode, respectively. We highlight our contributions in three-fold in the light of previous literature works. First, a bound of malware infection rate for each scheme is provided by applying the wireless network capacity theories. Second, the impact of mobility on malware propagations has been studied. Third, discussion of the relationship between different schemes and practical applications is provided. Numerical simulations and detailed performance analysis show that the Broadcast Scheme with Spread Mode is most dangerous in the sense of malware propagation speed in WANETs, and mobility will greatly increase the risk further. The results achieved in this paper not only provide insights on the malware propagation characteristics in WANETs, but also serve as fundamental guidelines on designing defense schemes.

With the ubiquitous deployment of the mobile devices and the explosive growth of Internet traffic, an emerging method called association rules mining (ARM) is proposed to solve the problem of mining potential value of existing big data. However, massive ARM methods focus on positive rules which are easy to ignore interesting information because of negative ones. This paper studies a practical problem of combing negative rules in ARM research. Specifically, we propose a rule certainty updating strategy (RCUS) to combine positive rules with negative rules, which consists of two parts: initialization and updating. To solve the large scale problem with negative rules, the proposed strategy decomposes the large scale problem into several relatively small ones by an improved multiobjective evolutionary algorithm (MOEA) with gene representation and certainty. Simulation results show that our method is outstanding when the scale of attributes and examples is increasing.

With the ubiquitous deployment of the mobile devices with increasingly better communication and computation capabilities, an emerging model called spatial crowdsourcing is proposed to solve the problem of unstructured big data by publishing location-based tasks to participating workers. However, massive spatial data generated by spatial crowdsourcing entails a critical challenge that the system has to guarantee quality control of crowdsourcing. This paper first studies a practical problem of task assignment, namely reliability aware spatial crowdsourcing (RA-SC), which takes the constrained tasks and numerous dynamic workers into consideration. Specifically, the worker confidence is introduced to reflect the completion reliability of the assigned task. Our RA-SC problem is to perform task assignments such that the reliability under budget constraints is maximized. Then, we reveal the typical property of the proposed problem, and design an effective strategy to achieve a high reliability of the task assignment. Besides the theoretical analysis, extensive experimental results also demonstrate that the proposed strategy is stable and effective for spatial crowdsourcing.

Fog computing, known as “cloud closed to ground,” deploys light-weight compute facility, called Fog servers, at the proximity of mobile users. By precatching contents in the Fog servers, an important application of Fog computing is to provide high-quality low-cost data distributions to proximity mobile users, e.g., video/live streaming and ads dissemination, using the single-hop low-latency wireless links. A Fog computing system is of a three tier Mobile–Fog–Cloud structure; mobile user gets service from Fog servers using local wireless connections, and Fog servers update their contents from Cloud using the cellular or wired networks. This, however, may incur high content update cost when the bandwidth between the Fog and Cloud servers is expensive, e.g., using the cellular network, and is therefore inefficient for nonurgent, high volume contents. How to economically utilize the Fog–Cloud bandwidth with guaranteed download performance of users thus represents a fundamental issue in Fog computing. In this paper, we address the issue by proposing a hybrid data dissemination framework which applies software-defined network and delay-tolerable network (DTN) approaches in Fog computing. Specifically, we decompose the Fog computing network with two planes, where the cloud is a control plane to process content update queries and organize data flows, and the geometrically distributed Fog servers form a data plane to disseminate data among Fog servers with a DTN technique. Using extensive simulations, we show that the proposed framework is efficient in terms of data-dissemination success ratio and content convergence time among Fog servers.

Multi-radio multi-channel (MRMC) is a promising approach to relieve the overload caused by the explosive growth of video streaming traffic in wireless mesh networks (WMNs). Previous studies have shown that in MRMC WMNs, network capacity can be increased significantly by proper design of channel assignment and routing algorithm. Multi-path routing can make good use of the network capacity improvement of MRMC WMNs. Multi-path routing has been applied in wired and wireless networks for load balancing or congestion control. However, it remains a challenge in MRMC WMNs. In this paper, we first discuss how to find multiple high-quality paths from source to destination while considering the interference between each other. Then we focus on the rate allocation among multiple paths and formulate it as a max-min problem which can be transformed to a linear programming (LP) problem. Finally, we propose a joint multi-path discovery and rate allocation algorithm. We evaluate this algorithm through simulations. Results show that our algorithm not only increases the network capacity, but also keeps the average end-to-end delay over all video streaming sessions at a low level.

Cellular networks are now facing severe traffic overload problems due to the explosive growth of mobile data traffic. One of the promising solutions is to offload part of the traffic through WiFi. In this paper, we investigate an oligopoly offloading market, where several Mobile Virtual Network Operators (MVNOs) compete to serve end users using the network infrastructure leased from the host Mobile Network Operator (MNO) at the wholesale market. First, we study the competitive interactions among the MVNOs considering the overload problems of the offloading market. Specially, we formulate the interactions as a non-cooperative inventory competition game, where each MVNO determines the amount of cellular traffic it can provide to end users (named as the traffic inventory of each MVNO in this paper) simultaneously. We analyze and derive the existence of the Cournot equilibrium using game theory. Furthermore, we study the impact of the MNO's wholesale price strategy on the market equilibrium. Based on these analysis, we find the optimal initial inventory strategy for these competitors according to the Cournot equilibrium. Finally, our simulations present the process of achieving the market equilibrium and illustrate the impact of the host MNO to the MVNOs.

Abstract Distributed caching‐empowered wireless networks can greatly improve the efficiency of data storage and transmission and thereby the users' quality of experience (QoE). However, how this technology can alleviate the network access pressure while ensuring the consistency of content delivery is still an open question, especially in the case where the users are in fast motion. Therefore, in this paper, we investigate the caching issue emerging from a forthcoming scenario where vehicular video streaming is performed under cellular networks. Specifically, a QoE centric distributed caching approach is proposed to fulfill as many users' requests as possible, considering the limited caching space of base stations and basic user experience guarantee. Firstly, a QoE evaluation model is established using verified empirical data. Also, the mathematic relationship between the streaming bit rate and actual storage space is developed. Then, the distributed caching management for vehicular video streaming is formulated as a constrained optimization problem and solved with the generalized–reduced gradient method. Simulation results indicate that our approach can improve the users' satisfaction ratio by up to 40%. Copyright © 2015 John Wiley & Sons, Ltd.

Abstract In delay and disruption tolerant networks, the contacts among nodes are intermittent. Because of the importance of data access, providing efficient data access is the ultimate aim of analyzing and exploiting disruption tolerant networks. Caching is widely proved to be able to improve data access performance. In this paper, we consider caching schemes for broadcasting and multicasting to improve the performance of data access. First, we propose a caching algorithm for broadcasting, which selects the community central nodes as relays from both network structure perspective and social network perspective. Then, we accommodate the caching algorithm for multicasting by considering the data query pattern. Extensive trace‐driven simulations are conducted to investigate the essential difference between the caching algorithms for broadcasting and multicasting and evaluate the performance of these algorithms. Copyright © 2016 John Wiley & Sons, Ltd.

At present, single network and technology could be impotent when facing: 1) the rocketing proliferation of mobile devices; and 2) the heterogeneity of data services and users' contexts. Therefore, offloading some specific traffic to other networks is a natural yet effective solution. To this end, this paper engineers the cellular offloading oriented vehicular ad hoc networks (VANETs), which concentrate on offloading users' bandwidth-hungry traffic in vehicular environment. Specifically, a two-phase resource allocation process is adopted, where utilization patterns of both wireless and backhaul links are studied for the sake of resource exploitation efficiency, with considerations on practical issues including link quality variety, fairness and caching. The former is formulated as an integer linear programming (ILP) problem aiming at system throughput maximization, and a heuristic algorithm is developed as solution due to the problem's NP-hardness nature. The latter's objective is identified and a simple implementation algorithm is designed correspondingly. Extensive simulations are conducted and the results show the effectiveness and efficiency of the proposed methods.

Driven by the ever-growing expectation of ubiquitous connectivity and the widespread adoption of IEEE 802.11 networks, it is not only highly demanded but also entirely possible for in-motion vehicles to establish convenient Internet access to roadside WiFi access points (APs) than ever before, which is referred to as Drive-Thru Internet. The performance of Drive-Thru Internet, however, would suffer from the high vehicle mobility, severe channel contentions, and instinct issues of the IEEE 802.11 MAC as it was originally designed for static scenarios. As an effort to address these problems, in this paper, we develop a unified analytical framework to evaluate the performance of Drive-Thru Internet, which can accommodate various vehicular traffic flow states, and to be compatible with IEEE 802.11a/b/g networks with a distributed coordination function (DCF). We first develop the mathematical analysis to evaluate the mean saturated throughput of vehicles and the transmitted data volume of a vehicle per drive-thru. We show that the throughput performance of Drive-Thru Internet can be enhanced by selecting an optimal transmission region within an AP's coverage for the coordinated medium sharing of all vehicles. We then develop a spatial access control management approach accordingly, which ensures the airtime fairness for medium sharing and boosts the throughput performance of Drive-Thru Internet in a practical, efficient, and distributed manner. Simulation results show that our optimal access control management approach can efficiently work in IEEE 802.11b and 802.11g networks. The maximal transmitted data volume per drive-thru can be enhanced by 113.1% and 59.5% for IEEE 802.11b and IEEE 802.11g networks with a DCF, respectively, compared with the normal IEEE 802.11 medium access with a DCF.

The routing efficiency in Delay Tolerant Networks (DTN) with social characteristics degrades owing to intermittent connection and high latency. Additionally, congestion is another issue because of the limited resources of nodes. To solve these problems, an improved Socially Aware Congestion Control algorithm (SACC) is proposed. In this algorithm, the social features and the congestion level of the node are utilized to construct a Social Congestion Metric (SCM). In the forwarding process, messages are forwarded to the nodes with higher SCM. When the congestion occurs, the node calculates the social links of itself with every message's destination node, and then drops the message with minimum social link rather than random dropping. Simulation results show that in the acceptable range of delay tolerance, the proposed algorithm improves the delivery probability, decreases the dropping probability and reduces the overhead.

Concurrent programs are known to be difficult to test and maintain. These programs often fail because of concurrency bugs caused by non-deterministic interleavings among shared memory accesses. Even though a concurrency bug can be detected, it is still hard to isolate the root cause of the bug, due to the challenge in understanding the complex thread interleavings or schedules. In this paper, we propose a practical and precise isolation technique for concurrent bugs called Pinso that seeks to exploit the non-deterministic nature of concurrency bugs and accurately find the root causes of program error, to further help developers maintain concurrent programs. Pinso profiles runtime inter-thread interleavings based on a set of summarized memory access patterns, and then, isolates suspicious interleaving patterns in the triaging phase. Using a filtration-oriented scheduler, Pinso effectively eliminates false positives that are irrelevant to the bug. We evaluate Pinso with 11 real-world concurrency bugs, including single- and multi-variable violation, from sever/desktop concurrent applications (MySQL, Apache, and several others). Experiments indicate that our tool accurately isolates the root causes of all the bugs.

Anypath routing can improve the end-to-end throughput by exploiting the broadcast nature of wireless communication media in wireless networks. Although anypath routing has been extensively studied in recent years, the problem of anypath routing in wireless networks with directional antennas has not been fully investigated. To the best of our knowledge, we are the first to study the joint problem of antenna direction scheduling and transmission rate selection for anypath routing in wireless networks with directional antennas. In this paper, we present a Directional antenna based Shortest Multirate Anypath routing algorithm (DSMA), which is proven to compute the optimal anypath routing strategy. We integrate our algorithm with a well-known opportunistic routing protocol MORE, and extensively evaluate its performance. Our evaluation results show that our algorithm can achieve at least 34.0% higher end-to-end throughput, in the median case; and at least 29.9% shorter mean end-to-end packet delay, than the single-rate anypath routing protocol.

The recent advances in wireless communication techniques have made it possible for fast-moving vehicles to download data from the roadside communications infrastructure [e.g., IEEE 802.11b Access Point (AP)], namely, Drive-thru Internet. However, due to the high mobility, harsh, and intermittent wireless channels, the data download volume of individual vehicle per drive-thru is quite limited, as observed in real-world tests. This would severely restrict the service quality of upper layer applications, such as file download and video streaming. On addressing this issue, in this paper, we propose ChainCluster, a cooperative Drive-thru Internet scheme. ChainCluster selects appropriate vehicles to form a linear cluster on the highway. The cluster members then cooperatively download the same content file, with each member retrieving one portion of the file, from the roadside infrastructure. With cluster members consecutively driving through the roadside infrastructure, the download of a single vehicle is virtually extended to that of a tandem of vehicles, which accordingly enhances the probability of successful file download significantly. With a delicate linear cluster formation scheme proposed and applied, in this paper, we first develop an analytical framework to evaluate the data volume that can be downloaded using cooperative drive-thru. Using simulations, we then verify the performance of ChainCluster and show that our analysis can match the simulations well. Finally, we show that ChainCluster can outperform the typical studied clustering schemes and provide general guidance for cooperative content distribution in highway vehicular communications.

Dynamic spectrum access (DSA) can be leveraged by introducing external spectrum sensing for secondary users (SUs) to overcome the hidden primary users (PUs) problem and improve spectrum utilization. In this paper, we investigate the DSA networks with external sensors, i.e., external sensing agents, to utilize spectrum access opportunities located in cellular frequency bands. Considering the diversity of SUs' demands and the secondary bandwidths discovered by external sensors, it is critical to manage the detected spectrum resources in an efficient way. To this end, we formulate the resource management problem in the DSA networks as a dynamic resource demand-supply matching problem, and propose a cooperative matching solution. Specifically, spectrum access opportunities are classified into two types by the resource block size: massive sized blocks and small sized blocks. For the former type, SUs are encouraged to share the whole time-frequency block via forming coalitional groups with a "wholesale" sharing approach. For the latter type, the resource "aggregation" sharing approach is proposed to meet the time-frequency demand of individual SUs. To further reduce the delay in the spectrum allocation and compress the matching process, we develop a distributed fast spectrum sharing (DFSS) algorithm, which can deal with both two aforementioned types of resource sharing cases. Simulation results show that the DFSS algorithm can adapt to the dynamic spectrum variations in the DSA networks and the average utilization of detected spectrum access opportunities reaches nearly 90%.

Asynchronous system provides great performance improvement for wireless ad hoc networks, such as anti-jamming, collision reduction and device simplification. Nevertheless, new media access and routing protocols are required to assist the asynchronous system, e.g., a neighbor discovery algorithm, which is the first step in the initialization of wireless ad hoc networks. In the past few years, a number of algorithms have been proposed for neighbor discovery. However, most of them only consider synchronous system and cannot work efficiently in asynchronous system. In this paper, firstly, we propose an analytical model for an 1-way asynchronous system in wireless ad hoc networks with directional antennas. Then, we compare the time-slot consumption in asynchronous system to complete the neighbor discovery process with that in synchronous system. Finally, in order to improve the performance of the neighbor discovery process, we extend the 1-way asynchronous discovery algorithms to a 2-way asynchronous discovery algorithm. To the best of our knowledge, this is the first practical analytical model of 2-way asynchronous neighbor discovery algorithm with directional antennas.

Due to the unpredictability of continuous data in distributed applications, it is hard for system to deal with data explosion in limited time. As a result, traditional static data storage technology fails to meet the demands for real-time data processing. To improve processing ability, many parallel processing structures are proposed, which brings up the problem that how the parallel machines can be scheduled to maximize their efficiency. Accordingly, a dynamic assignment scheduling algorithm for stream computing is proposed and a stream query graph is built to calculate the weight of every edge. The edge with the minimum weight is selected to send tuples. Simulation results show that the proper number of the logic machines could dramatically reduce system response time. Furthermore, system context switching is reduced by increasing the number of tuples sent every time.

The recent advances in wireless communication techniques have made possible for vehicles to download from the roadside communications infrastructure, namely drive-thru Internet. However, due to the fast-motions, harsh and intermittent wireless channels, the download volume of individual vehicles per drive-thru is quite limited as observed in real-world tests. This severely restricts the service quality of upper-layer applications, such as file download and video streaming. To address this issue, we take a historical approach by evaluating the integrated download throughput of a cooperative vehicle group in the highway environment. In specific, we first introduce a practical microscopic vehicular mobility model, which takes the randomness of speed update and safety distance requirement into account. Then, we analyze and formulate the number of contending vehicles within the coverage range of access point (AP) in the single-lane highways scenario, which can also be easily extended into the multi-lane highways scenario. Furthermore, we derive the data download volume by a vehicle per drive-thru, and analyze the relationship between the mobility speed and the data download volume. Finally, we derive the number of cooperative vehicles required for completing a download task in our investigated highways drive-thru Internet. The analytical model and evaluation results provide general guidance for cooperative content distribution and protocol design in drive-thru Internet.

This paper proposes an algorithm of data subcarrier designing to apply the tone reservation(TR) peak-to-average power ratio (PAPR) reduction algorithm in OFDM-based wireless communication systems and overcome the high computational cost issue. Different from the existing works, the proposed algorithm focuses on designing data subcarriers, controlling both the iteration times and the number of subcarriers. The new algorithm exhibits similar performance as the traditional TR algorithm with lower computational complexity and the ability to control the number of used subcarriers. Simulation results show that the proposed algorithm can significantly reduce the PAPR by only 2 or 3 iterations.

Low-density parity-check (LDPC) codes are playing an important role in modern wireless communication systems such as WiMAX due to their Shannon limit approaching error correction performance. To lower the decoding threshold of LDPC codes, this paper develops a novel multi-layer iterative decoding scheme using deterministic bits for multimedia communication systems. These deterministic bits serve as known information in the LDPC decoding process to reduce the redundancy during data transmission. Unlike the existing work, our proposed scheme addresses the controllable deterministic bits, such as MPEG null packets, rather than the widely investigated protocol headers. Simulation results show that our proposed scheme can achieve considerable gain in WiMAX networks.

Directional antennas provide great performance improvement for wireless networks, such as increased network capacity and reduced energy consumption. Nonetheless new media access and routing protocols are required to control the directional antenna system. One of the most important protocols is neighbor discovery, which is aiming at setting up links between nodes and their neighbors. In the past few years, a number of algorithms have been proposed for neighbor discovery with directional antennas. However, most of them cannot work efficiently when taking into account the collision case that more than one node exist in one directional beam. For practical considerations, we propose a new neighbor discovery algorithm to overcome this shortcoming. Moreover, we present a novel and practical mathematical model to analyze the performance of neighbor discovery algorithms considering collision effects. Numerical results clearly show our new algorithm always requires less time to discover the whole neighbors than previous ones. To the best of our knowledge, it is the first complete, practical analytical model that incorporates directional neighbor discovery algorithms.

Directional antennas offer great performance improvement for mobile ad hoc networks, but this improvement requires new mechanisms at medium access and networking layer. One of the most important protocols is neighbor discovery aiming at setting up links between nodes and their neighbors. This paper proposes a mathematical framework of a scan-based algorithm (SBA) for neighbor discovery, taking into account the case that more than one node exist in one directional beam. The analysis adopts detailed model for the discovery process and derives expression for the average number of slots required to discover all the neighbor nodes. Numerical results indicate the superiority of the proposed model.

Time efficiency is a basic characteristic for spectrum management and sharing in cognitive radio networks (CRN). In this paper, we introduce an incremental metric time into dynamic spectrum management and sharing problem, which could make the spectrum resource management more reasonable. On the one hand, to motivate the idle spectrum holders to share the spectrum more actively and regulate the spectrum leasing markets better , a spectrum management rule (SMR) is introduced. Accordingly, a spectrum lease rule (SLR) is proposed from the perspective of factual application requirements of unlicensed users (UUs). One the other hand, we formulate the spectrum sharing process as a two-dimensional packing problem, in which UUs utilize the spectrum resource through forming cooperative groups (CG). Finally, a distributed fast spectrum sharing algorithm (DFSS) is proposed to realize the process of CG forming promptly. Simulation demonstrates that DFSS algorithm can adapt to the cognitive radio networks effectively, and the average spectrum utilization ratio can reach about 83.42%.

In this paper, we propose a modification to Belief Propagation (BP) decoding algorithm for LDPC codes. The modification is to attenuate the check to bit extrinsic logarithm likelihood ratio by a factor α, when sudden sign change happens. This modification can be applied to both the standard BP algorithm and the joint row and column (JRC) BP algorithm. Simulation results show that the BER and WER performance of both traditional BP and JRC BP algorithms is improved by this method. The expense of the proposed modification is a slight increase in the average number of decoding iterations.

This paper investigates the design of LDPC codes over mobile DTV multipath channels. Most of the existing LDPC codes are optimized for additive white Gaussian noise (AWGN) channel, and not feasible to encounter the long burst error occurring in mobile DTV channel. Accordingly, we study the error propagation statistics of decision feedback equalizer (DFE) and formulate it into a gated noise model. To achieve good error correction in burst error channel, we proposed a class of dual-degree IRA codes to balance the metrics of decoding threshold and robustness. Extensive simulation results are presented in this paper to justify the performance of dual-degree IRA codes over gated noise model.

This paper investigates the use of ATSC M/H digital television (DTV) signal for location finding. In comparison to satellite based location finding system, DTV signals have higher field strength, wider bandwidth, lower frequency band, and DTV transmission towers are pervasively available everywhere. They can be used for indoor and mobile location finding in major cities where satellite based system might not function well. The ATSC receiver can obtain the multiple transmitter impulse responses and signal arrival times using the embedded RF watermark (RFWM) signal, and then derives its geographic coordinates based on the position of ATSC transmitters. As a critical step of this process, the transmitter identification in mobile environment has significant impact on the overall accuracy of location finding. In this paper, we present extensive analytical and simulation results to demonstrate the performance of RFWM technology over mobile channels.