Radio Frequency Identification (RFID) technology plays a pivotal role in modern applications ranging from retail and logistics to healthcare and security. However, a fundamental challenge persists in large-scale RFID systems: maximizing the coverage capacity of readers – the ability to reliably identify and communicate with the maximum number of tags within their operational range. While previous research has explored various aspects of RFID performance, the systematic optimization of coverage capacity remains underinvestigated. This paper addresses this gap by developing a comprehensive framework that integrates theoretical analysis with practical implementation strategies. We first establish a novel coverage capacity model that incorporates critical factors such as tag spatial distribution and link loss dynamics, providing a theoretical foundation for determining the upper bounds of reader performance. Building on this, we propose a cutoff-power-based optimization approach that dynamically adapts to real-world conditions without relying on predefined system parameters. Furthermore, to extend coverage across larger areas, we investigate advanced multi-reader configurations and present strategic deployment methodologies. Our framework is designed to characterize the baseline coverage capacity of existing RFID readers, rather than to enlarge the interrogation zone through additional hardware or protocol modifications. Moreover, it can be naturally extended to advanced configurations such as MIMO or phased-array systems once their antenna parameters are specified. The effectiveness of our approach is validated through extensive experiments using commercial RFID hardware, demonstrating measurable improvements in coverage capability. By bridging theoretical principles with practical constraints, this work offers actionable insights for designing and deploying high-performance RFID systems.

With the widespread adoption of smart home devices, there is a growing need for third-party device monitoring. Rapidly identifying device types from online traffic is essential for timely device detection, serving as a prerequisite for effective device supervision. As most smart home devices employ proprietary protocols, their communication traffic often lacks distinctive payload content. Existing methods typically rely on statistical features of data packets in idle traffic, combined with classification learning models, and commonly use fixed-time-window sampling for data collection. However, idle traffic from devices comprises multiple session flows, each often exhibiting distinct periodicity, which can lead to inaccurate feature extraction when fixed-length sampling is applied. To address this, we propose a smart home device identification method based on period-adaptive traffic fingerprinting. This method utilizes Fourier transform to analyze the periodicity of session flows, enabling adaptive partitioning of traffic samples based on their periodic characteristics. For rapid identification, key packets in the periodic traffic are first identified through clustering, followed by the extraction of packet header features and locality-sensitive hashing of the payload to construct packet-level traffic fingerprints. A hierarchical matching mechanism based on header and payload features is then employed to achieve device type identification. Experimental results on a public dataset demonstrate that the proposed method achieves an identification accuracy of 98.82%, outperforming existing baseline methods. In real-world smart home scenarios, the method enables rapid packet-level matching, providing identification results before a complete traffic period is reached, thus offering a responsive and efficient solution for device monitoring.

Adversarial examples generated in digital space may fail to work in the physical world because the recapture process will ruin the adversarial property of the examples. Several approaches have been proposed to generate adversarial examples that can survive in the physical world, they however either introduce markedly perceptible patterns (e.g., adversarial patches) or suffer from a low attack success rate due to improper perturbation propagation. In this work, we propose PRIA, a frequency-based approach to generating Physically Robust and Imperceptible Adversarial examples. PRIA reforms the pipeline of perturbation generation such that adversarial property of the generated examples retains after the recapture process. The experimental results reveal that PRIA outperforms state-of-the-art solutions, improves the attack success rate in the physical world by up to 19%, and meanwhile achieves the highest perceptual quality.

In the field of AI security, the vulnerability of deep neural networks has garnered widespread attention. Specifically, the sensitivity of DNNs to adversarial examples (AEs) can lead to severe consequences, even small perturbations in input data can result in incorrect predictions. AEs demonstrate transferability across models, however, targeted attack success rates (TASRs) remain low due to significant differences in feature dimensions and decision boundaries. To enhance the transferability of targeted AEs, we propose a novel approach by introducing Inverse Target Gradient Competition (ITC) and Spatial Distance Stretching (SDS) in the optimization process. Specifically, we utilize a twin-network-like framework to generate both non-targeted and targeted AEs, introducing a new competition mechanism ITC where non-targeted adversarial gradients are applied each epoch to hinder the optimization of targeted adversarial perturbations, thus enhancing robustness in targeted attacks. Additionally, a top-k SDS strategy is employed, guiding AEs to penetrate target class regions in the latent multi-dimensional space while globally distancing from multiple closest non-targeted regions, ultimately achieving optimal adversarial transferability. Compared with state-of-the-art competition-based attacks, our method demonstrates significant transferability advantages, with average transferable TASRs improved by 16.1% and 21.4% on mainstream CNNs and ViTs, respectively, while also achieving an unmatched breaking-through defense capability.

Wireless-based human activity recognition has gained increasing attention due to its low cost and non-invasiveness. Among them, RFID stands out for its passive nature and low power consumption. However, existing RFID gesture recognition systems typically assume static device deployment, limiting their applicability in mobile scenarios. To address this, we propose RF-movdev, an RFID-based gesture recognition frame-work that functions reliably under uniform device motion. By introducing a phase correction model, we compensate for motion-induced signal distortion, enabling accurate segmentation, feature extraction, and classification. Experiments under various conditions including different motion speeds, users, and environments demonstrate that RF-movdev improves classification accuracy from 0.14 to 0.61, and achieves up to 0.96 in static settings.

The wide adoption of encryption network traffic protocols, such as TLS/SSL, poses great challenges in the detection and recognition of network traffic. Recently, deep learning techniques have been exploited to detect malicious encrypted traffic. While achieving good performance, deep learning models can be bypassed due to their vulnerabilities to adversarial attacks. There has been some work on generating adversarial traffic to evade deep learning-based systems, however, they fail to generate traffic that complies with network constraints and does not work in practical scenarios. In this paper, we propose a method that can generate legitimate traffic and evade deep models in practical scenarios. The effectiveness of the method comes from two novel designs. First, the perturbations are added to only the payload field to generate legitimate packets. Second, the perturbations are generated in a way that adversarial examples with different multiple of the perturbations can both evade the detection system. Thus, the traffic generated with our method can be restored while all previous works fail to do so. We further designed a joint training method to improve the evasion rate of the generated traffic. Experimental results demonstrated that traffic generated by our method can evade state-of-the-art deep learning detection models with an overall escape success rate of higher than 94 %.

Falls are significant hazard to the health and safety of elderly individuals. Designing an alarm system capable of detecting fall events is crucial to mitigate these life-threatening risks. Compared to traditional methods, WiFi-based solutions have garnered extensive attention in recent years due to non-contact sensing nature and low-cost deployment advantages. While existing approaches have achieved high fall recognition accuracy, they still encounter inevitable delays in practice. These delays are mainly caused by limitations in signal segmentation, leading to recognition outcomes only after the activity has concluded. Moreover, existing methods overlook the continuity of human behaviors, reducing model robustness and increasing application constraints. To address these issues, this paper proposes PreFall, a WiFi-based fall detection method that achieves ongoing fall recognition before the activity ends. We adopt a deep model with attentional sentence embedding and propose a hybrid loss strategy. They are supposed to minimize the required sample observation for lower latency and guide the model to correctly detect fall events when multiple activities occur consecutively. Experimental results indicate that PreFall advances fall detection time by an average of 1.5 seconds and maintains a recognition accuracy of 88% when user behaves continuously.

Tactics and techniques information in Cyber Threat Intelligence (CTI) represent the objectives of attackers and the means through which these objectives are achieved. The classification of tactics and techniques descriptions in CTI has been extensively studied to assist security experts in interpreting attack patterns. Although many recent studies have applied various deep learning methods to enhance classification performance, they mainly focus on improving performance from an average or top perspective. However, the imbalance between tactical and technical tag samples, as well as text sparsity, may lead to poor model performance, which has been under-explored. To address these issues, we propose a new tactics and techniques classification model based on adversarial contrastive learning and meta-path (TTC-ACLM). In TTC-ACLM, a novel text representation learning module is first designed. It includes pre-trained language model (PLM) and contrastive adversarial methods, which can better adapt to categories with smaller sample sizes while obtaining better text representations. Then, heterogeneous information networks are used to model the rich relationships between texts and labels (tactics and techniques), which can merge additional information, e.g., processes and tools, to address text sparsity. Next, we defined a meta-path based classifier learning module that maps text, tactics, and meta-path based context to a set of classifiers, which are applied to the text representation generated by the text representation module for better classification. Finally, the classification performance is further improved through the tactics and techniques correlation enhancement matrix. Through in-depth research, we demonstrate that the proposed model can effectively address the impact of sample imbalance and text sparsity. Extensive experimental results indicate that TTC-ACLM achieves state-of-the-art performance.

Machine learning-based Android malware detection has consistently demonstrated superior results. However, with the continual evolution of the Android framework, the efficacy of the deployed models declines markedly. Existing solutions necessitate frequent and expensive model retraining to resist the constant evolution of malware accompanying Android framework updates. To address this, we introduce a solution called ASDroid, which generalizes specific APIs into similar API clusters to counteract evolving Android malware threats. One primary challenge lies in identifying analogous API clusters that correspond to specific APIs. Our approach involves extracting semantic information from open-source API source code to construct a heterogeneous information graph, and utilizing embedding algorithms to obtain semantic vector representations of APIs. APIs that are close in embedding distance are presumed to have similar semantics. Our dataset encompasses Android applications spanning nine years from 2011 to 2019. In comparison to existing Android malware detection model aging mitigation solutions like APIGraph, SDAC and MaMaDroid, ASDroid demonstrates greater accuracy and more effective at resisting continuously evolving malware.

A boundary is a physical or virtual line that marks the edge or limit of a specific region, which has been widely used in many applications, such as autonomous driving, virtual wall, and robotic lawn mowers. However, none of existing work can well balance the deployability and the scalability of a boundary. In this paper, we propose a brand new RFID-based virtual boundary scheme together with its detection algorithm called RF-Boundary, which has the competitive advantages of being battery-free and easy-to-maintain. We develop two technologies of phase gradient and dual-antenna AoA to address the key challenges posed by RF-boundary, in terms of lack of calibration information and multi-edge interference. Besides, we consider the presence of multipath in the real world applications, model the effect on signals in the dynamic scenarios, and demonstrate the robustness of our phase gradient-based scheme under multipath. We implement a prototype of RF-Boundary with commercial RFID systems and a mobile robot. Extensive experiments verify the feasibility as well as the good performance of RF-Boundary, with a mean detection error of only 8.6 cm.

For the creation of wireless network applications, node locations are frequently necessary. However, communication effectiveness, measurement accuracy, and localization stability will be low in irregular multi-hop networks when locating nodes using conventional algorithms. To this end, a novel cooperative localization algorithm using expected minimum segments (LEMS, for short) is proposed in this paper. LEMS begins by measuring the distance between paired nodes, which is completed along with network initialization. Then, each unlocated node constructs its own sub-network, including it, based on the error characteristics among anchor nodes. Finally, each unlocated node searches for its estimated location in its sub-region based on the objective function generated by the chaotic mapping. Simulation results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art regarding efficiency, accuracy, and stability for various irregular networks. Specifically, our proposed algorithm achieves a median improvement in localization accuracy of 0.62 to 29.57 times and a reduction in the range of localization errors of 0.06 to 16.8 times.

While decentralized training is attractive in multi-agent reinforcement learning (MARL) for its excellent scalability and robustness, its inherent coordination challenges in collaborative tasks result in numerous interactions for agents to learn good policies. To alleviate this problem, action advising methods make experienced agents share their knowledge about what to do, while less experienced agents strictly follow the received advice. However, this method of sharing and utilizing knowledge may hinder the team's exploration of better states, as agents can be unduly influenced by suboptimal or even adverse advice, especially in the early stages of learning. Inspired by the fact that humans can learn not only from the success but also from the failure of others, this paper proposes a novel knowledge sharing framework called Cautiously-Optimistic kNowledge Sharing (CONS). CONS enables each agent to share both positive and negative knowledge and cautiously assimilate knowledge from others, thereby enhancing the efficiency of early-stage exploration and the agents' robustness to adverse advice. Moreover, considering the continuous improvement of policies, agents value negative knowledge more in the early stages of learning and shift their focus to positive knowledge in the later stages. Our framework can be easily integrated into existing Q-learning based methods without introducing additional training costs. We evaluate CONS in several challenging multi-agent tasks and find it excels in environments where optimal behavioral patterns are difficult to discover, surpassing the baselines in terms of convergence rate and final performance.

The training of multi-agent reinforcement learning (MARL) tasks with the public goods dilemma (PGD) is difficult because the selfish actions of individual agents for high personal rewards may reduce the collective utility of the whole group. Existing solutions to this problem, e.g., reward gifting or intrinsic rewards, although inducing cooperation among agents in small groups, cannot guarantee fairness among agents’ policies and fail to achieve optimal group utility in large-scale systems. In this paper, we propose F4PGD, an effective method to train large-scale MARL tasks with PGD in a decentralized manner, which is inspired by Adam’s equity theory that the match between a person’s payoff and his contribution is the key incentive for people to contribute to the common good. In F4PGD, a mechanism is designed to match an agent’s reward with its contribution, which suppresses agents from taking a free ride and meanwhile encourages well-learned agents to contribute to public goods. Experimental results show that F4PGD effectively learns optimal policies for the whole group and guarantees fairness among agents in several typical MARL tasks with PGD.

A boundary is a physical or virtual line that marks the edge or limit of a specific region, which has been widely used in many applications, such as autonomous driving, virtual wall, and robotic lawn mowers. However, none of existing work can well balance the cost, the deployability, and the scalability of a boundary. In this paper, we propose a new RFID-based boundary scheme together with its detection algorithm called RF-Boundary, which has the competitive advantages of being battery-free, low-cost, and easy-to-maintain. We develop two technologies of phase gradient and dual-antenna DoA to address the key challenges posed by RF-boundary, in terms of lack of calibration information and multi-edge interference. We implement a prototype of RF-Boundary with commercial RFID systems and a mobile robot. Extensive experiments verify the feasibility as well as the good performance of RF-Boundary.

With the popularity of smart homes, the security issues of IoT devices have garnered significant attention, particularly the device pairing process, which is crucial for secure access and authorized use. However, current research on the communication security during this process remains insufficient. This paper aims to thoroughly analyze the security of the IoT device pairing process. The pairing process is first described using a state transfer model and divided into four phases: device discovery, device networking, remote authentication and remote binding. Subsequently, the different implementations adopted by different vendors in each specific phase are analyzed for the security vulnerabilities they may cause. These vulnerabilities are verified through experimental tests, involving the observation of multiple real devices, monitoring of traffic data, and application of attack methods, revealing existing vulnerabilities and deficiencies in some devices. Finally, based on the experimental results, targeted security improvement recommendations are proposed to enhance the overall security of the devices.

Enterprises face increasingly complex and frequent security threats, presenting significant challenges for timely prevention and response. Traditional log-based intrusion detection systems often rely on known attack signatures, limiting their ability to detect novel or evolving threats. Supervised anomaly detection methods, while leveraging machine learning techniques, are constrained by the scarcity of labeled attack samples, leading to gaps in detecting real-world attack variations. To address these limitations, this paper proposes a lightweight anomaly detection framework tailored for relatively stable server environments. The approach constructs provenance graphs from audit logs, extracts local subgraphs centered on process nodes, and utilizes Simhash for semantic embedding and frequency analysis. By combining locality-sensitive hashing with the K-medoids clustering algorithm, the method establishes a robust normal behavior model to detect anomalies. Experimental evaluations on public datasets and high-performance computing platforms demonstrate that the proposed method achieves 97% detection accuracy while significantly reducing the time costs compared to existing methods.

With the widespread adoption of IoT devices, their inadequate security measures make them increasingly susceptible to malicious attacks. Consequently, accurate device identification has become a critical task for safeguarding network security and privacy. This paper introduces IFPH, a novel method for IoT device fingerprinting and identification based on periodic traffic payload hashing. By exploiting the inherent periodicity in idle traffic, IFPH uses Discrete Fourier Transform (DFT) to extract the traffic's periodicity and applies Locality-Sensitive Hashing (LSH) to process packet payloads within each period. This method generates distinctive device fingerprints, facilitating efficient and reliable device identification. Unlike previous methods, IFPH addresses the inaccuracies associated with fixed-time window fingerprinting and eliminates the need for complex feature extraction or model training. Experimental results reveal that IFPH surpasses existing techniques, achieving accuracy and recall rates exceeding 95% on publicly available datasets.

Generating transferable adversarial examples is a challenging issue in adversarial example attacks. Existing works on transferable adversarial examples generation mainly focus on models with similar architectures and trained on the same data domain. However, in practice, information such as the model architecture type and training data domain is unlikely to be revealed in deployed models. In this work, we introduce the Universal Cross-domain Generator (UCG), a pioneering framework for transferable adversarial examples that is the first to simultaneously address both cross-domain and cross-architecture challenges in adversarial attacks. The design of UCG is mainly inspired by two key observations. First, there exists some commonality in attention regions even when the structures of models are different. Second, there exists prevalent instability of intermediate-feature maps across cross-domain models. We accordingly design anattention transfermechanism and aroughness abatementmechanism to enhance the cross-architecture and cross-domain transferability of the generated adversarial examples. Moreover, we propose anintegrated transformation processingtechnique to improve the transferability of the generated adversarial examples under different transformations. Experimental results demonstrate that, compared with state-of- the-art solutions, UCG improves the average transferable attack success rate by 15.3%, 7.9%, and 8.2% in the cross-architecture task (convolutional neural networks (CNNs) to vision transformers (ViTs)), coarse-grained cross-domain tasks, and fine-grained cross-domain tasks, respectively.

Adversarial example attacks are deemed to be a serious threat to deep neural network (DNN) models. Generating adversarial examples in white-box settings has been well-studied, however, it remains challenging to generate transferable adversarial examples that successfully attack black-box models. This work proposes Foolmix, a novel method for generating transferable adversarial examples for black-box attacks. The design of Foolmix is inspired by our observation that adversarial examples with high transferability usually carry multi-class features in the latent space of DNN models. Thus, we propose a dual-blending strategy that blends the image with a set of random pixel-blocks and blends the gradient by calculating the loss of the blended image for both the ground-truth label and a set of random labels. The dual-blending strategy pressures the example to penetrate multiple class regions and gain multi-class features in the latent space, greatly enhancing the transferability of the generated adversarial example. However, the randomness in the blending process might also pressure the example to approach the boundary of the original class region, which lowers the robustness of the example. To mitigate this problem, we further propose an update method in the starting forward direction to guide the generated adversarial example to go deep into multi-class adversarial regions while being globally far away from the original class region. Compared to state-of-the-art transformation-based attacks, Foolmix significantly enhances the transferability of generated adversarial examples, boosting the average transferable attack success rate by 13.2% and 16.9% on mainstream CNNs and ViTs respectively, while achieving better defense breakthrough ability.

Domain adaptation leverages labeled data from a source domain to learn an accurate classifier for an unlabeled target domain. Since the data collected in practical applications usually contain noise, the weakly-supervised domain adaptation algorithm has attracted widespread attention from researchers that tolerates the source domain with label noises or/and features noises. Several weakly-supervised domain adaptation methods have been proposed to mitigate the difficulty of obtaining the high-quality source domains that are highly related to the target domain. However, these methods assume to obtain the accurate noise rate in advance to reduce the negative transfer caused by noises in source domain, which limits the application of these methods in the real world where the noise rate is unknown. Meanwhile, since source data usually comes from multiple domains, the naive application of single-source domain adaptation algorithms may lead to sub-optimal results. We hence propose a universal and scalable weakly-supervised domain adaptation method called PDCAS to ease restraints of such assumptions and make it more general. Specifically, PDCAS includes two stages: progressive distillation and domain alignment. In progressive distillation stage, we iteratively distill out potentially clean samples whose annotated labels are highly consistent with the prediction of model and correct labels for noisy source samples. This process is non-supervision by exploiting intrinsic similarity to measure and extract initial corrected samples. In domain alignment stage, we consider Class-Aligned Sampling which balances the samples for both source and target domains along with the global feature distributions to alleviate the shift of label distributions. Finally, we apply PDCAS in multi-source noisy scenario and propose a novel multi-source weakly-supervised domain adaptation method called MSPDCAS, which shows the scalability of our framework. Extensive experiments on Office-31 and Office-Home datasets demonstrate the effectiveness and robustness of our method compared to state-of-the-art methods.

Performing accurate sensing in diverse environments is a challenging issue in wireless sensing technologies. Existing solutions usually require collecting a large number of samples to train a classifier for every environment, or further assume similar sample distribution between different environments such that a model trained in one environment can be transferred to another. In this paper, we propose RF-Siamese, an RFID-based gesture sensing approach that achieves comparable accuracy to existing solutions but requires only a few samples in each eivironment. RF-Siamese leverages Siamese networks to distinguish different gestures with only a small number of samples and is enhanced by several novel designs to achieve high accuracy in diverse environments. First, the network structure and parameters (e.g., loss function and distance metric) are carefully designed to be suitable for RFID gesture recognition. Second, a permutation-based dataset generation strategy is proposed to make full use of the collected samples to enhance the recognition accuracy. Third, a template matching method is proposed to extend the Siamese network to classify multiple gestures. Extensive experiments on commercial RFID devices demonstrate that RF-Siamese achieves a high accuracy of 0.93 with only one sample of each gesture when recognizing 18 different gestures, while state-of-the-art approaches based on transfer learning and meta learning achieve an accuracy of only 0.59 and 0.70, respectively.

WiFi-based wireless sensing has gained popularity for enabling smart indoor services, one of which is fall detection which plays a vital role in mitigating health risks for elders. Previous approaches have treated daily activities as independent events and built models to distinguish falls from others. However, human activities are usually adjoint in practice, e.g., the elder may suddenly fall when she walks. This adjoining introduces shared features between different activities, thereby affecting the classification performance. To address this problem, we propose Fall-attention, an attention-based fall detection method that can focus on the features related to fall events and suppress interference of irrelevant activities to improve performance. Its basic idea is to produce a task-oriented feature representation of fall events inside the signal using attention-based sentence embedding techniques and Recurrent Neural Network (RNN). We incorporate multi-task learning into Fall-attention by adopting multiple independent classification modules. This enables the model to explore different regions of the signal, capturing the composition of adjoint activities. A series of signal preprocessing and data enhancement techniques are also adopted to promote model training. Experimental results of the dataset containing adjoint activities demonstrate the superiority of Fall-attention over previous methods, which achieves an average accuracy of 95%.

As an essential part of the website, JavaScript greatly enriches its functions. At the same time, JavaScript has become the most common attack payload on malicious websites. Although researchers are constantly proposing methods to detect malicious JavaScript, the emergence of obfuscation technology makes it difficult for previous approaches to detect disguised malicious JavaScript effectively. To solve this problem, we find that there are fixed templates for generating obfuscated code, which makes the original and obfuscated script have a mapping relationship in their structure. The structure information of the code is critical for malicious detection. Therefore, this paper proposes TransAST, a novel static detection method for obfuscated malicious JavaScript. Our approach's key is restoring the obfuscated JavaScript structure information by training the machine translation model. The experiment shows it can achieve 91.35% accuracy and 94.57% recall in the public dataset, which is 5.5% and 10.94% higher than the existing optimal method.

Learning effective strategies in sparse reward tasks is one of the fundamental challenges in reinforcement learning. This becomes extremely difficult in multi-agent environments, as the concurrent learning of multiple agents induces the non-stationarity problem and sharply increased joint state space. Existing works have attempted to promote multi-agent cooperation through experience sharing. However, learning from a large collection of shared experiences is inefficient as there are only a few high-value states in sparse reward tasks, which may instead lead to the curse of dimensionality in large-scale multi-agent systems. This paper focuses on sparse-reward multi-agent cooperative tasks and proposes an effective experience-sharing method, Multi-Agent Selective Learning (MASL), to boost sample-efficient training by reusing valuable experiences from other agents. MASL adopts a retrogression-based selection method to identify high-value traces of agents from the team rewards, based on which some recall traces are generated and shared among agents to motivate effective exploration. Moreover, MASL selectively considers information from other agents to cope with the non-stationarity issue while enabling efficient training for large-scale agents. Experimental results show that MASL significantly improves sample efficiency compared with state-of-the-art MARL algorithms in cooperative tasks with sparse rewards.

To recognize the target classes with only a few samples, few-shot learning (FSL) uses prior knowledge learned from the source classes and is usually expressed as a special domain adaptation problem. However, Existing few-shot learning methods make the implicit assumption that the few target class samples are from the same domain or different domain as the source class samples, which greatly limits their application in the wild. This paper introduces a few-shot learning method in multiple scenarios which requires no prior knowledge on the label set. For a given target domain labels set, it may overlap with the set of source domain labels to varying degrees, thereby bringing up an additional class gap based on the domain gap. In order to solve this problem in a unified framework, we propose a novel domain adaptation network which is designed to address a specific challenge: How to achieve domain adaptation whilst maintaining source/target per-class discriminativeness when the target domain label set is unseen. Our solution is to design corresponding soft label transfer network and minimax entropy network for different target domain label set, then we quantify the transferability of the source domain label set during the training process to discover the relationship between the source domain label set and the target domain label set. Further, we broaden the model's understanding of the data by learning from self-supervised signals how to solve a jigsaw puzzle on the same sample. Extensive experiments show that our model outperforms the state-of-the-art models.

Adversarial attacks reveal the inherent vulnerability of deep neural networks, which face serious security issues for their security. Among them, the attack against the Deep Neural Network (DNN) application used in the Industrial Internet of Things (IIoT) is a key area in adversarial attacks. Adversarial examples generated by attackers by adding human-undetectable interference to legitimate examples may cause models to make wrong decision results, resulting in serious accidents. Many detection technologies have been proposed to mitigate the harm of adversarial examples to neural networks, among which the methods based on the difference of feature attribution between normal examples and adversarial examples show state-of-the-art detection performance, but they suffer from detection efficiency. In this work, we focus on improving the detection efficiency of the feature-attribution-based detection methods. We observe that there is still a significant difference in the feature attribution distribution of a normal image and an adversarial image even only some pixels in the image are processed, which can be verified by utilizing the Kolmogorov-Smirnov test. Based on this observation, we first adopt a variety of strategies to sample partial pixels in an image and then utilize the selected pixels to train a feature-attribution-based detector for detecting adversarial examples. Extensive experiments conducted on four datasets (MNIST, CIFAR-10, SVHN, CIFAR-100) against various attacks proved that the detection efficiency of the accelerated detection method is improved (for example, the average execution time was increased by 8.7 times on CIFAR-10) while the detection performance maintains state-of-the-art.

The number of devices connected to the Internet has been exploding in recent years, and the wide range of device types poses a serious challenge for asset management and maintenance. We need to know if IoT devices are under cyberattack and if there are devices that violate our privacy, such as pinhole cameras. Traffic-oriented IoT device type identification has become an effective method to prevent cyberattacks and manage assets, but at this stage, in the face of the proliferation of novel IoT devices, the current mainstream IoT device type identification methods are difficult to identify them successfully. At the same time, for a significant number of lightweight IoT devices, most identification methods are simply unable to make correct identifications because the traffic generated by these devices is too little. In this paper, we propose IoT-Siamese, a type identification method for IoT devices based on few-shot traffic, which mainly relies on Siamese network to solve the problem of few samples. Experiments show that our proposed identification method has high identification accuracy for those devices that generate a small volume of traffic, and effectively identify novel devices that join the network.

Recently there has been many studies on backdoor attacks, which involve injecting poisoned samples into the training set in order to embed backdoors into the model. Existing multiple poisoned samples attacks usually randomly select a subset from clean samples to generate the poisoned samples. Filtering-and-Updating Strategy (FUS) has shown that the poisoning efficiency of each poisoned sample is inconsistent and random selection is not optimal. However, FUS does not fully considered the selection of multiple poisoned samples, there are still some issues with the selection of multiple poisoned samples. In this paper, we formulate the selection of multiple types of poisoned samples as a multi-objective optimization problem and proposed a Multiple Poisoned Samples Selection Strategy (MPS) to solve the issue. Unlike FUS, we consider the potential of clean samples that are not selected as to become efficient poisoned samples. Specifically, we use a weight-based contribution approach to calculate the contribution of each sample (clean sample and poisoned sample) during the training process from multiple dimensions. Finally, based on the greedy approach, we retain a subset of samples with the largest contribution in each dimension through iterations. We evaluate the effectiveness of MPS on various attack methods, including BadNet, Blended, ISSBA, and WaNet, as well as benchmark datasets. The experimental results on CIFAR-10 and GTSRB show that MPS can increase the attack strength by 1.45% to 18.34% compared to RSS and 0.43% to 10.84% compared to FUS in multiple poisoned samples attacks, thereby enhancing the stealthiness of the attack. Meanwhile, MPS is suitable for black-box settings, meaning that poisoned samples selected in one setting can be applied to other settings.

Deep neural network (DNN) models have been widely used in many tasks due to their superior performance. However, DNN models are usually vulnerable to adversarial example attacks, which limits their applications in many safety-critic scenarios. How to effectively detect adversarial examples to enhance the robustness of DNN models has attracted much attention in recent years. Most adversarial example detection methods require modifying or retraining the model, which is impractical and reduces the classification accuracy of normal examples. In this paper, we propose an adversarial example detection approach that does not require modification of the DNN models and meanwhile retains the classification accuracy of normal examples. The key observation is that when we transform the input example with some operations (e.g., masking a pixel with a reference value), feed the transformed example to the target model, and use the output of the intermediate layers to predict the label of the example, the generated label sequences of adversarial examples will be extremely discrepant but the label sequences of normal examples keep nearly unchanged. Motivated by this observation, we design an approach to detect adversarial examples based on the label sequence discrepancy (LSD) of the given examples. The experimental results against five mainstream adversarial attacks on three benchmark datasets demonstrate that LSD outperforms the state-of-the-art solutions in the detection rate of adversarial examples. Moreover, LSD performs well at various confidence levels and exhibits good generalizability between different attacks.

How to efficiently coordinate multiple readers to work together is critical for high throughput in RFID systems. Existing researchs focus on designing efficient reader scheduling strategies that arrange adjacent readers to work in different time to avoid signal collisions. However, the impact of unbalanced tag number of readers on tag read throughput is still challenging. In RFID systems, the distribution of tags is usually variable and uneven, making the number of tags covered by each reader (i.e., the load) imbalanced. This imbalance leads to different execution time for readers: the heavily loaded readers take longer time to collect all tags, while the other readers whose finish execution earlier have to wait in vain. To avoid this useless waiting and improve the system throughput, this paper focuses on the load balancing problem of multiple readers, which is an NP-hard problem. In this paper, we design heuristic algorithms to adjust readers interrogation regions and efficiently balance their loads. The amazing advantage of our algorithm is that it can be adopted by almost all existing protocols in multi-reader systems, including the reader scheduling protocol, to improve system throughput. Extensive experiments demonstrate that our algorithm can significantly improve the throughput in various scenarios.

RFID systems have been widely deployed for various applications such as inventory control, retail management, and object tracking. In many scenarios, coarse-grained system management of tag categories is more common than traditional system management of individual tags. Existing works on tag category management require knowing category IDs in advance, however, few protocols have been specially designed to obtain category IDs in multi-category RFID systems. In this paper, we proposeCIP, a time-efficient protocol specially designed to collect category IDs in multi-category RFID systems. The challenge in solving this problem is to avoid repeatedly collecting category IDs from multiple tags belonging to the same category. We address this challenge by squeezing tags in the same category into the same time slot and letting them reply to the reader simultaneously. Considering that the reader may receive signals from different tags in a slot, we exploit the Manchester coding to decode the aggregated signals. With this design, CIP collects each category ID only once and thus achieves high time efficiency by avoiding redundant identification of the same category ID. We further enhance CIP by utilizing the lightweight vectors to specify the order of tags’ replying and avoid useless slots. Rigorous theoretical analysis is presented to optimize the performance of CIP and guidelines on how to set optimal parameters to minimize the overall execution time are given. We conduct extensive experiments to evaluate the performance of our protocols. The experimental results show that our protocols can significantly improve time efficiency by 67 percent when compared with the state-of-the-art solutions.

Lip reading can help people with speech disorders to communicate with others and provide them with a new channel to interact with the world. In this paper, we design and implementHearMe, an accurate and real-time lip-reading system built on commercial RFID devices. HearMe can be used to accurately recognize different words in a pre-defined vocabulary without limitations in light conditions and can be used in multiple user scenarios by leveraging RFID's ability in identifying different users. We design an effective data collection strategy to well capture the tiny and complex signal patterns caused by mouth motion and propose a set of algorithms to extract signal profiles related to mouth motions and mitigate interference factors like multi-path. A carefully designed set of features, including time-domain statistical features and frequency-domain features, are then extracted from the signal to lift the recognition accuracy at the word level. To reduce training costs when the model is used in a new environment, a transfer-learning-based approach is adopted to enhance the robustness of the model in cross-environment scenarios. Experimental results show that HearMe detects speaking actions of the user with an accuracy higher than 0.95 and recognizes different words in a 20-words vocabulary with an average accuracy higher than 0.88. Moreover, the latency of HearMe ($\sim$150ms) is nearly two orders of magnitude less than traditional approaches, making it applicable to practical scenarios that require real-time lip reading.

Gesture recognition based on radio frequency identification (RFID) has attracted much research attention in recent years. Most existing RFID-based gesture recognition approaches use signal profile matching to distinguish different gestures, which incur large recognition latency and fail to support real-time applications. In this paper, we design and implement ReActor, a real-time and accurate gesture recognition system that recognizes a user's gestures with low latency and high accuracy even when the gestures'speed varies. ReActor combines the time-domain statistical features and the frequency-domain features to precisely represent the signal profile corresponding to different gestures. To maintain high accuracy across different environments, we preprocess the signals to remove reflection signals from surrounding objects and use only the signals related to gestures to train the classifier. Moreover, we train a classifier to predict the speed of the gesture and feed the extracted features to different classifiers according to the speed. We implement ReActor and evaluate its performance in different scenarios. Experimental results show that ReActor achieves an average accuracy of 97.2% in recognizing 18 different gestures with an average latency of 72 ms, more than two orders of magnitude faster than approaches based on profile template matching.

Although multistage tasks involving multiple sequential goals are common in real-world applications, they are not fully studied in multi-agent reinforcement learning (MARL). To accomplish a multi-stage task, agents have to achieve cooperation on different subtasks. Exploring the collaborative patterns of different subtasks and the sequence of completing the subtasks leads to an explosion in the search space, which poses great challenges to policy learning. Existing works designed for single-stage tasks where agents learn to cooperate only once usually suffer from low sample efficiency in multi-stage tasks as agents explore aimlessly. Inspired by human’s improving cooperation through goal consistency, we propose Multi-Agent Goal Consistency (MAGIC) framework to improve sample efficiency for learning in multi-stage tasks. MAGIC adopts a goal-oriented actor-critic model to learn both local and global views of goal cognition, which helps agents understand the task at the goal level so that they can conduct targeted exploration accordingly. Moreover, to improve exploration efficiency, MAGIC employs two-level goal consistency training to drive agents to formulate a consistent goal cognition. Experimental results show that MAGIC significantly improves sample efficiency and facilitates cooperation among agents compared with state-of-art MARL algorithms in several challenging multistage tasks.

RFID technologies have been widely used for item-level object monitoring and tracking in industrial applications. In this paper, we study the problem of range detection in a commodity RFID system, which aims to quickly figure out whether there are any target tags that hold specific data between a lower and upper boundary. This is important to help users pinpoint tagged objects of interest (if any) and give an early warning for reducing the potential risk, e.g., temperature monitoring for fire safety. We propose a time-efficient protocol called encoding range query (EnRQ). The basic idea is to use a sparse vector to separate target tags from the others with a few select commands. The sparse vector is specifically designed by encoding the tag’s data based on notational systems. We implement EnRQ in commodity RFID systems with no need for any hardware modifications. Extensive experiments show that EnRQ can improve the time efficiency by more than 40% on average, compared with the state-of-the-art.

The human can easily recognize the incongruous parts of an image, for example, perturbations unrelated to the image itself, but are poor at spotting the small geometric transformations. However, in terms of the robustness of deep neural networks (DNNs), the ability to properly recognize objects with small geometric transformations is still a challenge. In this work, we investigate the problem from the perspective of adversarial attacks: does the performance of DNNs degrade even when small geometric transformations are applied to images? To this end, we propose a novel adversarial attack method, called WBA, a Warping-Based Adversarial attack method, which does not introduce information independent of the original images but manipulates the existing pixels of the images by elastic warping transformations to generate adversarial examples that are imperceptible to the human eye. At the same time, existing adversarial attacks typically generate adversarial examples by modifying pixels in the spatial domain of the image, the addition of such perturbations introduces extra information unrelated to the image itself and is easily detected by the naked eyes. We demonstrate the effectiveness of WBA by extensive experiments on commonly used datasets, including MNIST, CIFAR10, and ImageNet. The results show that WBA can quickly generate adversarial examples with the highest adversarial strength, consumes less time, and can be comparable to optimization-based adversarial attack methods in image perception evaluation metrics such as LPIPS, SSIM, and far more than gradient direction-based iterative methods.

With the Android system becoming the most popular operating system for mobile smart terminals, it is more likely to be targeted by malware. Therefore, many researches of malicous detection have emerged. Most of the features extracted of current malicious detection are discrete, such as single permission, single API, single component, API sequences and so on. These features can only detect the maliciousness of Android applications, but cannot characterize the malicious behavior of Android applications through these features. In this paper,we propose a method to automatically mine malicious features by pruning the function call graph(FCG) of Android applications. These extracted features not only have a good representation for the malicious behavior of Android applications, but also can efficiently detect the malicious. The method uses simhash to characterize the pruned subgraphs of FCG, and selects the subgraphs which play a decisive role in determining maliciousness as malicious features. These malicious features are then used for malicious detection of Android applications. The verification on public datasets shows that our method has a good effect of more than 97% in malicous detection of Android applications.

RFID technology has been widely applied in a range of applications such as inventory control, warehouse management and supply chain logistics. Many practical applications need to search a given set of tags (calledwanted tags) to determine which of them are present in the system, which is usually calledtag searching. Existing tag searching protocols suffer performance bottleneck and the time efficiency and need to be improved. The bottleneck stems from two factors. First, the existing methods validate the wanted tags in a random way due to the randomness of the hash function, which unavoidably generate many useless slots. Second, in order to achieve the predefined reliability requirement, the existing methods have to repeatedly validate target tags multiple times. In this paper, we design new tag searching techniques of compact exclusive validation that break through the existing performance bottleneck from two aspects. First, our protocols avoid slot waste. Different from random tag validation, our protocols validate tags orderly by mapping the wanted tags and the slots in a one-to-one manner, which makes the reader be able to validate tags in every slot. Second, our protocols avoid repeated tag responding. By combining two lightweight indicators, we rapidly filter out non-wanted tags so that there is no interference when validating the wanted tags. Hence, we need to validate each wanted tag only once, which avoids redundant validation and greatly improves time efficiency. Our protocols work with the assumption that the rough number of tags in the system can be obtained by using existing estimation algorithms, but they do not need to know exactly which tags are in the system. Theoretical analysis illustrates our methods achieve linear time complexity. Extensive experimental results show that, our best protocol can improve the time efficiency by up to 81 percent when compared with the-state-of-art solution.

Weakly-supervised domain adaptation has been introduced to address the source domain with label noise or/and feature noise. However, the existing weakly-supervised domain adaptation methods only work under ideal assumptions, which assume either the annotated data of the target domain can be accessed or the noise rate of all the classes is identical and already known. This limits their practical application. To tackle this, we propose a universal weakly-supervised domain adaptation method called PDCAS which relaxes the ideal assumptions and makes it more general. Specially, PD- CAS includes two stages: progressive distillation and domain alignment. In progressive distillation, we iteratively distill out potentially corrected samples whose annotated labels are consistent with the prediction of model. By exploiting intrinsic similarity to extract initial corrected samples, this process does not need any supervision. In domain alignment, besides taking the global feature distributions into consideration, we also adopt Class-Aligned Sampling which balances the samples for both source and target domains to alleviate the shift of label distributions. Extensive experiments on Office-31 and Office-Home datasets demonstrate the effectiveness and robustness of our method compared to state-of-the-art methods.

Modern distributed storage systems are increasingly implementing erasure codes to obtain better storage performance. In such systems, it is desirable to regenerate a failed storage node in a cost-effective manner since node failures occur frequently in real-world storage networks. Fractional repetition (FR) codes are a special class of regenerating codes that enable efficient recovery of failed storage nodes. In this paper, we introduce expandable FR codes, wherein both the number of storage nodes and the capacity of each node in the storage systems can be readily expanded. We present explicit constructions of expandable FR codes by applying two families of combinatorial structures called embeddable quasi-residual designs and extendible t-designs. Moreover, we study the property of constructed codes for some special scenarios.

Radio-frequency identification (RFID) has been utilized in many applications, such as supply chain and stock management in supermarkets. RFID systems in such practical applications are inherently dynamic because tags may move in and out frequently. One important but challenging problem in such systems is how to estimate the number of dynamic tags fast and reliably. This article proposes effective solutions to this problem, which guarantee the accuracy of estimation and time efficiency. Especially, we want to simultaneously estimate the number of tags that moved out of the system (missing tags) and the number of tags that entered the system (unknown tags) in a specified time interval. We design a novel method called time slot reuse (TSR) that generates two logical frames corresponding to the two types of tags from only one physical frame. Based on TSR, we propose a protocol called SSR that can accurately estimate the number of dynamic tags by using the generated logic frames. However, the performance of SSR degrades significantly when the disparity between the number of the two types of tags is remarkable. We further propose an enhanced version of SSR (ESSR), which overcomes this drawback by partitioning the frame into ranges and mapping different types of tags into different ranges. Rigorous theoretical analysis is performed to tune parameters in SSR and ESSR to minimize the execution time. The simulation results demonstrate up to 80% improvement in time efficiency when compared with state-of-the-art solutions to the same problem.

Vital signs (e.g., respiration rate or heartbeat rate) sensing is of great importance to implement pervasive in-home healthcare. Traditional vital signs monitoring approaches usually require users to wear some dedicated sensors. These approaches are intrusive and inconvenient to use, especially for elderly people. Some non-intrusive vital signs monitoring approaches based on wireless sensing have been proposed in recent years. However, these approaches require the target user to be in situ during the monitoring process, which greatly limits their utilization in practical scenarios where the target users usually move around. In this paper, we propose RF-RMM, an RFID-based approach to accurate and continuous respiration monitoring for mobile users. The major challenge in respiration monitoring for moving people is that the tiny body displacement caused by the user's respiration is overwhelmed by the user's entire body movement. To address this issue, we propose a novel approach that uses a pair of tags to eliminate the effect of the user's body movement. We fuse the data from the paired tags to cancel the effect of the user's entire body movement and retain only the displacement caused by the user's respiration. Another challenging issue in implementing RF-RMM is how to resolve the phase ambiguity problem when the target user moves around, which becomes more serious than in the static case. We propose a distance tracking algorithm to track the phase transition during the user's movement, according to which the phase ambiguity problem can be well handled. We implement RF-RMM on commercial RFID devices and conduct extensive real-world experiments to evaluate its performance. The results show that RF-RMM achieves accurate respiration rate monitoring with an average error of 0.54 BPM in estimating different users' respiration rate and an average relative error of less than 13% in estimating the user's individual breath length.

The exploit kits (EKs) are used by attackers to distribute malware automatically and silently. Existing approaches to EKs detection usually need to perform dynamic analysis on the content contained in the network traffic, which requires dumping all the network traffic and thus causes high detection overhead. Although some approaches detect EKs based on static analysis, they usually fail to restore the complete attack path because of the obstruction set by the attackers. In this paper, we propose an approach that can detect EKs based on only information extracted by static analysis. Our method builds a graph for web sessions and extracts features from the graph to perform EKs detection. The built graph catches important structural characteristics of the interaction during EK attacks that were not revealed in existing methods, with which EKs can be detected with high accuracy. The experiments show that our method works well in both the ground-truth datasets and the latest practical cases. Our method can also identify the malicious websites concealed in EKs, which can further improve the efficiency of analysis.

By integrating the micro-sensor on RFID tags to obtain the environment information, the sensor-augmented RFID system greatly supports the applications that are sensitive to environment. To quickly collect the information from all tags, many researchers dedicate on well arranging tag replying orders to avoid the signal collisions. Compared to from all tags, collecting information from a part of tags (i.e., target tags) is more challenging because the collecting process is interfered by useless replying from non-target tags. The existing works of target tag information collection are designed for single reader systems. However, they cannot work efficiently in more common multi-reader scenarios, where each reader lacks knowledge of tag distribution among all readers. In this paper, we propose time-efficient protocols to collect target tag information in multi-reader systems. The high efficiency of our protocol is enabled by two novel designs. First, we develop a technique that quickly detects and silences non-target tags without a priori knowledge of which tags are in the readers' interrogation regions. Second, we design an allocation vector to efficiently arrange the replying order of only target tags. Different from previous bit-vector based approaches that make use of only singleton slots, our allocation vector approach also makes use of collision slots to speed up target tag information collection. We further propose an enhancement protocol which can reconcile the collision slots with higher probability and therefore collect information from more target tags simultaneously. The extensive simulation results demonstrate that our protocols significantly outperform the state-of-the-art protocols in terms of time-efficiency.

Radio frequency identification (RFID) has been widely used in many smart applications. In many scenarios, it is essential to know the ordering of a set of RFID tags. For example, to quickly detect misplaced books in smart libraries, we need to know the relative ordering of the tags attached to the books. Although several relative RFID localization algorithms have been proposed, they usually suffer from large localization latency and cannot support applications that require real-time detection of tag (product) positions like automatic manufacturing on an assembly line. Moreover, existing approaches face significant degradation in ordering accuracy when the tags are close to each other. In this paper, we propose RLLL, an accurate Relative Localization algorithm for RFID tags with Low Latency. RLLL reduces localization latency by proposing a novel geometry-based approach to identifying the V-zone in the phase reading sequence of each tag. Moreover, RLLL uses only the data in the V-zone to calculate relative positions of tags and thus avoids the negative effects of low-quality data collected when the tag is far from the antenna. Experimental results with commercial RFID devices show that RLLL achieves an ordering accuracy of higher than 0.986 with latency less than 0.8 seconds even when the tags are spaced only 7 mm from adjacent tags, in which case the state-of-the-art solutions only achieve ordering accuracy of lower than 0.8 with localization latency larger than 3 seconds.

Tag searching is a fundamental problem for a variety of radio frequency identification (RFID) applications. Prior works focus on single group searching, which refers to determining which ones in a given set of tags exist in the system. In this paper, we propose PTS, a protocol that can perform fast Parallel Tag Searching for multiple users simultaneously. Different from prior works that have to execute k times to search k groups separately, PTS obtains searching results for all the k groups with only one-shot execution. PTS achieves high parallelism due to some novel designs. First, we develop a grouping filter that encodes the membership of tags in different groups, with which non-target tags can be efficiently filtered out for all the k groups simultaneously. Second, we design two new codes, grouping code and mapping code, with which the remaining tags can quickly verify and confirm which group they belong to. We theoretically analyze how to set optimal parameters for PTS to minimize the execution time and conduct extensive simulation experiments to evaluate its performance. Compared with the state-of-the-art solutions, PTS significantly improves time efficiency in multiple group searching scenarios (by a factor of up to 7.54X when k = 10) and achieves the same time efficiency in single group searching scenarios.

We propose a new radio frequency identification (RFID) localization approach that achieves both low latency and high accuracy by fusing multiple type of signal features. Existing RFID tag localization approaches either suffer from large localization latency (e.g., approaches based on phase measurements), or cannot provide high localization accuracy (e.g., approaches based on received signal strength (RSS)). We propose a two-step approach that fuses phase measurements and RSS measurements to resolve this dilemma. First, coarse-grained RSS measurements are utilized to Figure out a small bounding box that encloses the position of the target tag. Second, fine-grained phase measurements are used to refine the position estimation of the target tag in the bounding box. Experimental results show that the proposed fusion approach achieves centimeter-level localization accuracy with less than 10 feature measurements, reducing localization latency by more than one order of magnitude when compared to state-of-the-art solutions.

With the massive deployment of IoT devices, the management of IoT devices becomes more and more important. In this paper, We only need the packet length the device sent to serves in 180s to identify the device. We evaluated the algorithms K-Nearest Neighbor, Random Forest, Suport Vector Machine and Multilayer Perceptron for classification. The results show that the Random Forest is the best and can achieve 99.6% if accuracy in the identification of devices. We also ranked the importance of 10 features related to packet length. Using the five most important features (media, mean, skewness, absolute energy, standard deviation and of packet length), we can achieve 99.5% accuracy on the public dataset and 99.29% accuracy on our dataset.

servers in the Internet are vulnerable to Web attacks, to detect Web attacks, a commonly used method is to detect anomalies in the request parameters by making regular-expression-based matching rules for the parameters based on known security threats. However, such methods cannot detect unknown anomalies well and they can also be easily bypassed by using techniques like transcoding. Moreover, existing anomaly detection methods are usually based on a single HTTP request, which is easy to ignore the attack behavior within a period of time, such as brute-force password cracking attack. In this paper, we propose an unsupervised W eb S ession A nomaly D etection method called WSAD. WSAD uses ten features of web session to perform anomaly detection. After extracting the ten features, WSAD uses the DBSCAN algorithm to cluster the features of each session and outputs the outliers found in the clustering process as anomalies. We evaluate the performance of WSAD on several datasets from multiple real websites of a company. The results indicate that WSAD could detect malicious behaviors that could not be detected by Web Application Firewall, and it almost has no false positives.

Web servers in the Internet are vulnerable to Web attacks. A general way to launch Web attacks is to carry attack payloads in HTTP request parameters, e.g. SQL Injection and XSS attacks. To detect Web attacks, a commonly used method is to detect anomalies in the request parameters by making regular-expression-based matching rules for the parameters based on known security threats. However, such methods cannot detect unknown anomalies well and they can also be easily bypassed by using techniques like transcoding. Moreover, existing anomaly detection methods are usually based on supervised learning methods that require a large number of high-quality labelled samples as training sets, which are difficult to obtain in real situations. In this paper, we propose an unsupervised HTTP Request Parameter Anomaly Detection method called RPAD. RPAD uses five features of HTTP request parameters to perform anomaly detection including type, length, number of tokens, encoding type and character feature. After extracting the five features, RPAD uses the DBSCAN algorithm to cluster the parameters of each target access request and outputs the outliers found in the clustering process as anomalies. We evaluate the performance of RPAD on several datasets from multiple real websites of a Cyber Security Company. The results indicate that RPAD is highly efficient in detecting deviating abnormal parameter values with an accuracy of 99%.

Billions of devices are connected to the Internet of Things (IoT). These devices generate a large volume of data, which poses an enormous burden on conventional networking infrastructures. As an effective computing model, edge computing is collaborative with cloud computing by moving part intensive computation and storage resources to edge devices, thus optimizing the network latency and energy consumption. Meanwhile, the software-defined networks (SDNs) technology is promising in improving the quality of service (QoS) for complex IoT-driven applications. However, building SDN-based computing platform faces great challenges, making it difficult for the current computing models to meet the low-latency, high-complexity, and high-reliability requirements of emerging applications. Therefore, a cloud-mobile edge computing (MEC) collaborative task offloading scheme with service orchestration (CTOSO) is proposed in this article. First, the CTOSO scheme models the computational consumption, communication consumption, and latency of task offloading and implements differentiated offloading decisions for tasks with different resource demand and delay sensitivity. What is more, the CTOSO scheme introduces orchestrating data as services (ODaS) mechanism based on the SDN technology. The collected metadata are orchestrated as high-quality services by MEC servers, which greatly reduces the network load caused by uploading resources to the cloud on the one hand, and on the other hand, the data processing is completed at the edge layer as much as possible, which achieves the load balancing and also reduces the risk of data leakage. The experimental results demonstrate that compared to the random decision-based task offloading scheme and the maximum cache-based task offloading scheme, the CTOSO scheme reduces delay by approximately 73.82%-74.34% and energy consumption by 10.71%-13.73%.

Malware detection is an important and challenging issue in the Android ecosystem. Many approaches have been proposed to distinguish malicious applications from benign ones, but few of them can represent the behavior patterns of malicious applications and help understand their intention. In this paper, we propose LSCDroid, a malware detecting approach that cannot only detect malware but also help understand the malware's intention by analyzing its behavior patterns. LSCDroid uses local sensitive application programming interface (API) invocation (LSAI) sequences as features to detect malware and represent different malicious behavior patterns. We first extract LSAI sequences of malicious applications based on their function-call graphs. After removing redundant sequences and merging fragmented ones, we obtain a set of LSAI sequences that can be used to effectively detect malicious applications. We further manually analyze the semantic of the obtained sequences and find that a large fraction of them can be used to characterize different behavior patterns of malware and help understand their intention, e.g., sending SMS message stealthily, obtaining geographical information, remote control, and root privilege. We design a machine learning based malware detection and classification algorithm by taking the obtained sequences as input features. Experimental results show that the accuracy and recall of LSCDroid on multiple datasets are both higher than 0.98. Meanwhile, LSCDroid can classify malware families with an accuracy higher than 0.96. Moreover, LSCDroid can represent the behavior patterns and help understand intention of malware by mapping their LSAI sequences to some typical malicious behaviors.

The blockchain uses a decentralized consensus mechanism to maintain the books in an immutable way, which ensures the blockchain smart contract system highly secure. In existing blockchain systems, all user information is disclosed in the blockchain. However, currently users begin to pay more and more attention to personal privacy, therefore the future blockchain smart contract system needs not only to keep immutability but also to protect user privacy. To achieve this goal, in this paper we propose a privacy-encrypted blockchain system, where all data is encrypted within a controllable period of time. Although the data is visible from a historical perspective, our design can effectively protect user privacy and against deceivers, making the system more secure and healthy.

Contactless gesture recognition has emerged as a promising technique to enable diverse smart applications, e.g., novel human-machine interaction. Among others, gesture recognition based on radio frequency identification (RFID) is preferred due to its prevalent availability, low cost, and ease in deployment. However, current RFID-based gesture recognition approaches usually use profile template matching to distinguish different gestures, making them suffer from large recognition latency and fail to support real-time applications. In this paper, we propose a real-time and accurate contactless RFID-based gesture recognition approach called ReActor. ReActor uses machine learning rather than time-consuming profile template matching to distinguish different gestures, and thus achieves both very low recognition latency and high recognition accuracy. The major challenge of our approach is to determine a set of suitable attributes that can preserve the profile features of the signals related to different gestures. We combine two types of attributes in ReActor: the statistics of the signal profile that characterize coarse-grained features and the wavelet (transformation) coefficients of the signal profile that characterize fine-grained local features, both of which can be calculated fast. Experimental results demonstrate that ReActor can recognize a gesture with average latency less than 51ms, two orders of magnitude faster than state-of-the-art approaches based on profile template matching. Furthermore, ReActor also achieves higher recognition accuracy than previous works due to its optimized attribute set.

Internet of Things (IoT) have been widely used in many fields including smart city, industry Internet and automatic driving. Because IoT end devices usually have only limited capability in computation and power supply, they are not suitable to execute energy-consuming computational tasks. In many cases, we need to offload computational tasks from IoT end devices to edge servers in order to save energy consumption on the end devices. This process is usually termed as computing offloading. In this paper, we study computing offloading in radio frequency identification (RFID) systems built with mobile readers. We analyze the energy consumption characteristics of different components in mobile RFID systems, based on which we propose a framework to perform energy-aware offloading for such systems. By using tag searching as an example, we illustrate how our framework can help offload computational intensive tasks to edge servers to save energy consumption on mobile readers while satisfying the constraint on total execution time. Simulation results shown that the energy consumption of mobile readers can be greatly reduced by using our offloading framework.

Localization plays a pivotal role in wireless sensor networks. Many range-based localization algorithms have been proposed for 2-D sensor networks or densely deployed 3-D sensor networks. However, range-based localization in sparse 3-D sensor networks is still a challenging problem, because the sparseness of the network makes it difficult to obtain a proper order of nodes to be sequentially localized. The patch-and-stitching localization strategy can conquer the sparseness problem in 2-D networks, but for 3-D networks it is still unknown how to uniquely merge two patches when there are not enough common nodes. In this paper, we solve this challenging problem by deriving the conditions under which two subnetworks can be uniquely merged. In the proposed approach, we treat the translation parameters as unknowns and form a set of equations with which the unknowns can be uniquely solved. The novelty of our algorithm also lies in that we exploit both common nodes and connecting edges among adjacent subnetworks to merge them, resulting in very high chances that two subnetworks can be merged. We conduct extensive simulation experiments to evaluate the performance of the proposed algorithm. The results show that the proposed algorithm could localize more than 90% of nodes in sparse 3-D networks with average node degree of 11 and anchor ratio of 5%, while the best existing solution can localize only 52% of nodes in the same situation.

Radio frequency identification (RFID)-based localization and activity recognition have attracted much research attention recently. They rely on accurate measurements of signal features, e.g., phase and received signal strength (RSS), in line-of-sight (LOS) condition to estimate the location or activity status of the target objects. However, the LOS requirement might be frequently breached by obstacles between reader and tags in real deployed RFID systems. The resulting non-LOS (NLOS) signal will greatly reduce localization or activity recognition accuracy. How to filter out NLOS in the localization/activity recognition process is therefore practically important for guaranteeing accuracy. In this paper, we propose the first LOS/NLOS path recognition approach to differentiate the signals by LOS path from the ones by NLOS path. The proposed approach is both precise (with precision higher than 0.95) and real-time in nature (with recognition delay less than 400 ms) due to the following innovative designs. First, we design a new metric that can precisely distinguish LOS and NLOS paths by considering the joint variance of phase and RSS. Second, we propose an efficient method to mitigate the negative impacts of phase ambiguity on recognition precision. Third, we sample over a selected subset of channels and use only a handful of readings to perform LOS/NLOS path recognition, which greatly reduces the recognition delay without sacrificing precision. We conducted extensive experiments with commercial-off-the-shelf RFID devices. The results show that our approach achieves high precision and recall in all testing cases, with a precision of up to 0.969 and a recall of up to 0.991. Furthermore, our approach can also distinguish between different types of obstacles with an accuracy as high as 0.93.

Through well-designed counterfeit websites, phishing induces online users to visit forged web pages to obtain their private sensitive information, e.g., account number and password. Existing antiphishing approaches are mostly based on page-related features, which require to crawl content of web pages as well as accessing third-party search engines or DNS services. This not only leads to their low efficiency in detecting phishing but also makes them rely on network environment and third-party services heavily. In this paper, we propose a fast phishing website detection approach called PDRCNN that relies only on the URL of the website. PDRCNN neither needs to retrieve content of the target website nor uses any third-party services as previous approaches do. It encodes the information of an URL into a two-dimensional tensor and feeds the tensor into a novelly designed deep learning neural network to classify the original URL. We first use a bidirectional LSTM network to extract global features of the constructed tensor and give all string information to each character in the URL. After that, we use a CNN to automatically judge which characters play key roles in phishing detection, capture the key components of the URL, and compress the extracted features into a fixed length vector space. By combining the two types of networks, PDRCNN achieves better performance than just using either one of them. We built a dataset containing nearly 500,000 URLs which are obtained through Alexa and PhishTank. Experimental results show that PDRCNN achieves a detection accuracy of 97% and an AUC value of 99%, which is much better than state-of-the-art approaches. Furthermore, the recognition process is very fast: on the trained PDRCNN model, the average per URL detection time only cost 0.4 ms.

Hybrid applications (apps) are becoming more and more popular due to their cross-platform capabilities and high performance. These apps use the JavaScript (JS) bridge communication scheme to interoperate between native code and Web code. Although greatly extending the functionalities of hybrid apps by enabling cross-language invocations and making them more powerful, the bridge communication scheme might also cause some new security issues, e.g., cross-language code injection attacks and privacy leaks. In this paper, we propose BridgeTaint, a bi-directional dynamic taint tracking method that can detect bridge security issues in hybrid apps. BridgeTaint uses a method different from existing ones to track tainted data: it records the taint information of sensitive data when the data are transmitted through the bridge, and uses a cross-language taint mapping method to restore the taint tags of corresponding data. Such a novel design enables BridgeTaint to dynamically track tainted data during the execution of the app and analyze hybrid apps developed using frameworks, which cannot be done with existing solutions based on static code analyses. Based on BridgeTaint, we implement the BridgeInspector tool to detect cross-language privacy leaks and code injection attacks in hybrid apps using JS bridges. A benchmark called BridgeBench is also developed for bridge communication security test. The experimental results on BridgeBench and 1172 apps from Android market demonstrate that BridgeInspector can effectively detect potential privacy leaks and cross-language code injection attacks in hybrid apps using bridge communications.

Software-Defined Networking (SDN) greatly simplifies middlebox policy enforcement. Middleboxes need tag packet headers to avoid forwarding ambiguity on SDN switches. In this paper, we present a new attack, called middlebox-bypass attack, to breach SDN-based middlebox policy enforcement. Such an attack manipulates a compromised switch to locally tag attacking packets without handing them over to the attached middlebox for inspection. Existing SDN security solutions, however, cannot detect the middlebox-bypass attack under practical constraints of efficiency, robustness, and applicability. We design and implement FlowCloak, the first protocol for per-packet real-time detection and prevention of middlebox-bypass attacks. FlowCloak enables middleboxes to generate tags that are probabilistically unknown to an attacker and confines it to only random guessing. We propose a multi-tag verification technique to address the tradeoff between FlowCloak robustness and TCAM usage by tag verification rules on the egress switch. Experiment results show that dozens of verification rules can confine the attacking probability under 0.1 %. FlowCloak imposes only a 0.3 ms packet processing delay on middleboxes and no obvious delay on the egress switch.

As one of the enabling technologies for Internet of Things (IoTs), radio frequency identification (RFID) has been widely adopted in many applications. Among others, RFID-based localization has attracted much research attention in recent years. Existing RFID localization algorithms are usually based on single signal feature, e.g., received signal strength (RSS) or phase information. These algorithms cannot achieve high localization accuracy and low delay simultaneously: Algorithms based on RSS usually suffer from low localization accuracy, while algorithms based on phase suffer from large localization delay because they need to collect a large number of phase readings to resolve phase ambiguity. In this paper, we propose an RFID localization algorithm that can achieve both high accuracy and low delay by fusing multiple types of signal features. We first use the RSS measurements to quickly shrink the possible region of the target tag, and then use phase measurements to refine the position estimation. Experiment results demonstrate the effectiveness of this novel design.

Along with the penetration of smart devices and mobile applications in our daily life, how to effectively manage the mobility issues in wireless networks becomes a challenging task. The ability to continuously and accurately track the target object’s position plays a vital role in mobility management. In this paper, we propose a novel indoor localization algorithm that fuses multiple signal features as the location fingerprints. The rationale that motivates our algorithm design stems from the following observation: although using one special signal feature (e.g., channel state information (CSI)) might achieve statistically higher accuracy than using another signal feature (e.g., received signal strength (RSS)), the accuracy for individual position estimations is usually diversified when only one signal feature is used in localization. For example, using RSS can obtain more accurate location estimation than using CSI for some individual positions. Thus, we propose a novel indoor localization algorithm that fuses multiple types of signal features as fingerprint of positions, which can effectively improve localization accuracy. We designed several fusion schemes and evaluated their performance. Experiments show that our algorithm achieves localization error below 0.5m and 1.1m in two typical indoor environments, about 30% lower than the accuracy of algorithms by fusing multiple signal features.

In this paper, we study the tag size profiling (TSP) problem in RFID systems with multiple readers, which is to estimate the number of tags in every subregion in the system covered by different set of readers. The TSF problem is vitally important to reader scheduling and many other related operations in large scale multi-reader RFID systems. To our knowledge, however, it is not well solved in previous researches. We propose a novel approach to the TSF problem. The key idea is to treat the size of subregions as variables and construct a linear system in these variables to solve them. We theoretically prove that for any multi-reader RFID system, a linear system that can be used to uniquely solve the variables corresponding to the subregion sizes can always be constructed. We then propose a time-efficient algorithm that uses two heuristics to quickly find enough linearly independent equations to construct the linear system. Extensive simulation results show that the proposed approach achieves very high accuracy. When the estimation results of individual readers contain 5% errors, our approach achieves median estimation error of smaller than 0.02 and 90-percentile estimation error of smaller than 0.04 in large systems containing more than one hundred readers.

Radio Frequency IDentification (RFID) plays a vital role in smart computing applications. Due to the limited communication range of individual RFID readers, large RFID systems deployed in real applications usually contain multiple readers. Existing reader scheduling algorithms either disallow adjacent readers to simultaneously work in order to avoid collisions among them, or simply activate all the readers to work together to exploit the parallel working of readers to increase identification throughput. In this paper, we propose a reader scheduling algorithm that tolerates collisions among readers but selects an optimal set of readers that can maximize tag identification throughput to work in parallel. The proposed algorithm thus achieves much higher tag identification throughput than existing solutions. Experiment results in a small testbed containing three readers show that, compared with the state-of-the-art solution, the proposed algorithm enhances tag identification throughput by 40%. Results from extensive simulation experiments further demonstrate that the proposed algorithm performs much better than existing solutions in large RFID systems. For example, the proposed algorithm achieves 132% higher identification throughput than previous best solution in systems containing more than one hundred readers when the readers are randomly deployed, meanwhile achieves much smaller identification delay.

Summary In service‐oriented cloud computing systems (CCSs), the aim of cloud service organizers (CSOs) is to achieve maximum profit by collecting metadata with low cost from big data reporters (BDRs) and to provide advanced services to customers at a high price. In these systems, BDRs receive payoffs by reporting metadata to CSOs and exchanging metadata with other BDRs, and customers expect to get high‐quality services at a low price. However, because the missing of a critical parameters decision model in such service‐oriented CCSs, it is difficult to measure key parameters in CCSs such as price and quality of services in the competitive market. In this paper, we propose a multiple game (MG) model to formulate the critical parameters decision process. In the MG model, there are multiple games: games among BDRs and games among CSOs under the rule of “survival of the fittest,” games between BDRs and CSOs under the rule of “the highest payoff first,” and games between customers and CSOs under the rule of “the lowest price and the highest quality of service (QoS) first.” With the proposed multiple game (MG) model, the optimal key parameters can be obtained and the Pareto‐optimal equilibrium point can be achieved. Extensive simulation results demonstrate the effectiveness and efficiency of the proposed MG model in dynamically deciding key parameters in CCSs.

An RFID system can greatly improve the efficiency of tagged object inventory setup and update. It is necessary to periodically take stock of tags and update the inventory accordingly (i.e., deleting absent tags and adding new tags) in dynamic scenarios such as warehouses and shopping malls. Fast tag stocktaking is critical for the dynamic RFID system management. Previous work can take stock of tags by either collecting IDs of all the tags in the system, which is known to be inefficient, or broadcasting a long indicator vector to save tag identification time, which is not compatible with current commercial-off-the-shelf (COTS) tags. In this paper, we propose HARN, a protocol that can quickly take stock of tags in dynamic RFID systems but is compatible with COTS RFID tags and easily applied in a real RFID system. HARN uses only one more hash in the standard EPC C1G2 protocol. It leverages the new hash to generate the random number (RN) for a tag that can be used for both channel contention and known tag recognition, which can save the tedious ID transmission from known tags to readers and greatly speed up the stocktaking of tags. Simulation results demonstrate that HARN improves stocktaking throughput by up to 3.8x when compared to the state-of-the-art solutions in dynamic RFID systems.

Fast tag identification is a fundamental challenging problem in multi-reader RFID systems. The challenge is how to effectively handle Reader-Tag (RT) collisions and Reader-Reader (RR) collisions among adjacent readers. These collisions are caused by interfering signals simultaneously transmitted by the readers, and may disallow adjacent readers to work together. Prior works tackle this problem by scheduling adjacent readers to work in different time slots. The readers that are selected to simultaneously work, however, are usually only a small proportion of the total readers. This greatly restricts the identification throughput. Our insightful investigation on the current tag identification protocol reveals that RT collisions are caused by asynchronous actions of readers. i.e., a reader transmits signal while its adjacent readers receive. We thus develop Slot Splitting, a technique that can completely eliminate RT collisions by synchronizing actions of readers. We also propose a reader selection algorithm that minimizes RR collisions by selecting a reader set with maximum reading efficiency. The combination of these new techniques inspires Federal, a Fast and efficient tag identification protocol with interference-elimination-based reader scheduling. To our knowledge, Federal is the first identification protocol that completely eliminates RT collisions and minimizes RR collisions in both regularly and randomly deployed multi-reader systems. We validate the feasibility of Slot Splitting with experiments on the USRP platform and evaluate the performance of Federal through extensive simulations. The results show that Federal can increase tag identification throughput by up to 218% compared with the state-of-the-art work.

Tag scanning is an important issue to dynamically manage tag IDs in radio frequency identification (RFID) systems. Different from tag identification that collects IDs of all the tags, tag scanning first verifies whether or not a responding tag has already been identified and retrieves its ID when the answer is yes, and collects the tag's ID only when it is unidentified. In this paper, we present the first study on spot scanning with a handheld reader, which aims to scan tags in the reader's interrogation range at an arbitrarily specified position in the system. Existing studies mainly focus on continuous scanning, and they are highly time inefficient in performing spot scanning. The inefficiency stems from the small overlap between tag populations in different spot scanning operations, in which case existing solutions cannot efficiently recognize unidentified tags. We develop a novel technique called LOCK to efficiently recognize unidentified tags even when the overlapped tags are few. LOCK does not simply use a tag's reply slot index but also compact short responses from tags to efficiently distinguish unidentified tags from identified ones. The valuable compact short responses are firstly investigated, which are the keys for efficient tag identification in the paper. Based on LOCK, three tag scanning protocols are proposed to solve the spot scanning problem. Simulation results show that, for spot scanning, our best protocol reduces per tag scanning time by up to 70 percent when compared with the state-of-the-art solution. Moreover, the proposed protocols can also be employed to perform continuous scanning with better time efficiency than the best existing solutions.

The radio frequency identification (RFID) technology is greatly revolutionizing applications such as warehouse management and inventory control in retail industry. In large RFID systems, an important and practical issue is tag searching: Given a particular set of tags called wanted tags, tag searching aims to determine which of them are currently present in the system and which are not. As an RFID system usually contains a large number of tags, the intuitive solution that collects IDs of all the tags in the system and compares them with the wanted tag IDs to obtain the result is highly time inefficient. In this paper, we design a novel technique called testing slot, with which a reader can quickly figure out which wanted tags are absent from its interrogation region without tag ID transmissions. The testing slot technique thus greatly reduces transmission overhead during the searching process. Based on this technique, we propose two protocols to perform time-efficient tag searching in practical large RFID systems containing multiple readers. In our protocols, each reader first employs the testing slot technique to obtain its local searching result by iteratively eliminating wanted tags that are absent from its interrogation region. The local searching results of readers are then combined to form the final searching result. The proposed protocols outperform existing solutions in both time efficiency and searching precision. Simulation results show that, compared with the state-of-the-art solution, our best protocol reduces execution time by up to 60 percent, meanwhile promotes the searching precision by nearly an order of magnitude.

Cloning attacks seriously impede the security of radio-frequency identification (RFID) applications. This paper tackles deterministic clone detection for anonymous RFID systems without tag identifiers (IDs) as a priori. Existing clone detection protocols either cannot apply to anonymous RFID systems due to necessitating the knowledge of tag IDs or achieve only probabilistic detection with a few clones tolerated. This paper proposes three protocols—BASE, DeClone, and DeClone+—toward fast and deterministic clone detection for large anonymous RFID systems. BASE leverages the observation that clone tags make tag cardinality exceed ID cardinality. DeClone is built on a recent finding that clone tags cause collisions that are hardly reconciled through rearbitration. For DeClone to achieve detection certainty, this paper designs breadth first tree traversal toward quickly verifying unreconciled collisions and hence the cloning attack. DeClone+ further incorporates optimization techniques that promise faster clone detection when clone ratio is relatively high. The performance of the proposed protocols is validated through analysis and simulation. This paper also suggests feasible extensions to enrich their applicability to distributed design.

Position information plays a pivotal role in wireless sensor network (WSN) applications and protocol/algorithm design. In recent years, range-free localization algorithms have drawn much research attention due to their low cost and applicability to large-scale WSNs. However, the application of range-free localization algorithms is restricted because of their dramatic accuracy degradation in practical anisotropic WSNs, which is mainly caused by large error of distance estimation. Distance estimation in the existing range-free algorithms usually relies on a unified per hop length (PHL) metric between nodes. But the PHL between different nodes might be greatly different in anisotropic WSNs, resulting in large error in distance estimation. We find that, although the PHL between different nodes might be greatly different, it exhibits significant locality ; that is, nearby nodes share a similar PHL to anchors that know their positions in advance. Based on the locality of the PHL, a novel distance estimation approach is proposed in this article. Theoretical analyses show that the error of distance estimation in the proposed approach is only one-fourth of that in the state-of-the-art pattern-driven scheme (PDS). An anchor selection algorithm is also devised to further improve localization accuracy by mitigating the negative effects from the anchors that are poorly distributed in geometry. By combining the locality-based distance estimation and the anchor selection, a range-free localization algorithm named Selective Multilateration (SM) is proposed. Simulation results demonstrate that SM achieves localization accuracy higher than 0.3 r , where r is the communication radius of nodes. Compared to the state-of-the-art solution, SM improves the distance estimation accuracy by up to 57% and improves localization accuracy by up to 52% consequently.

Coverage of interest points and network connectivity are two main challenging and practically important issues of Wireless Sensor Networks (WSNs). Although many studies have exploited the mobility of sensors to improve the quality of coverage and connectivity, little attention has been paid to the minimization of sensors' movement, which often consumes the majority of the limited energy of sensors and thus shortens the network lifetime significantly. To fill in this gap, this paper addresses the challenges of the Mobile Sensor Deployment (MSD) problem and investigates how to deploy mobile sensors with minimum movement to form a WSN that provides both target coverage and network connectivity. To this end, the MSD problem is decomposed into two sub-problems: the Target COVerage (TCOV) problem and the Network CONnectivity (NCON) problem. We then solve TCOV and NCON one by one and combine their solutions to address the MSD problem. The NP-hardness of TCOV is proved. For a special case of TCOV where targets disperse from each other farther than double of the coverage radius, an exact algorithm based on the Hungarian method is proposed to find the optimal solution. For general cases of TCOV, two heuristic algorithms, i.e., the Basic algorithm based on clique partition and the TV-Greedy algorithm based on Voronoi partition of the deployment region, are proposed to reduce the total movement distance of sensors. For NCON, an efficient solution based on the Steiner minimum tree with constrained edge length is proposed. The combination of the solutions to TCOV and NCON, as demonstrated by extensive simulation experiments, offers a promising solution to the original MSD problem that balances the load of different sensors and prolongs the network lifetime consequently.

Radio-Frequency Identification (RFID) technology brings revolutionary changes to many fields like retail industry. One important research issue in large RFID systems is the identification of unknown tags, i.e., tags that just entered the system but have not been interrogated by reader(s) covering them yet. Unknown tag identification plays a critical role in automatic inventory management and misplaced tag discovery, but it is far from thoroughly investigated. Existing solutions either trivially interrogate all the tags in the system and thus are highly time inefficient due to re-identification of already identified tags, or use probabilistic approaches that cannot guarantee complete identification of all the unknown tags. In this paper, we propose a series of protocols that can identify all of the unknown tags with high time efficiency. We develop several novel techniques to quickly deactivate already identified tags and prevent them from replying during the interrogation of unknown tags, which avoids re-identification of these tags and consequently improves time efficiency. To our knowledge, our protocols are the first non-trivial solutions that guarantee complete identification of all the unknown tags. We illustrate the effectiveness of our protocols through both rigorous theoretical analysis and extensive simulations. Simulation results show that our protocols can save up to 70 percent time when compared with the best existing solutions.

Radio-Frequency Identification (RFID) technology has fostered many object monitoring systems. Along with this trend, tagged objects' value and privacy become a primary concern. A corresponding important problem is to verify the intactness of a set of tagged objects without leaking tag identifiers (IDs). However, existing solutions necessitate the knowledge of tag IDs. Without tag IDs as a priori, this paper studies intactness verification in anonymous RFID systems. We identify three critical solution requirements, that is, deterministic verification, anonymity preservation, and scalability. We propose Cardiff and Divar, two crypto-free, lightweight protocols that isolate tag IDs from intactness verification and satisfy solution requirements. Cardiff explores tag cardinality as intactness proof while Divar leverages Direct-Sequence Spread Spectrum (DSSS) enabled RFID. Both analytical and simulation results demonstrate that Cardiff and Divar can satisfy the requirements of accuracy, privacy, and scalability.

The Radio Frequency IDentification (RFID) technology provides a promising solution to location discovery in indoor environments. Existing RFID reader positioning algorithms usually use all the collected reference tags to determine the position of the target reader, and thus are time-consuming as well as susceptible to the communication irregularity between the reader and reference tags. Especially, they usually perform poorly when the target reader is near the wall or at the corner. In this paper, we propose ArPat, an Accurate RFID reader Positioning algorithm that uses mere boundary reference Tags to calculate the position of the reader. ArPat uses only boundary tags to determine the position of the target reader, which effectively mitigates the negative impact of communication irregularity on the localization accuracy. The localization accuracy of ArPat is higher than 0.2 ft when the space between references tags is 1 ft. Compared with state-of-the-art solutions for RFID reader positioning, ArPat improves localization accuracy by up to 42 percent and 36 percent on average. Furthermore, it uses a geometric approach rather than iterative optimization approaches employed by previous solutions, making it superior in time efficiency. Compared with previous solutions, the computational time of ArPat is nearly two orders of magnitude less. This is critical for a localization system to provide real time location discovery and tracking services.

Tag identification is the most fundamental problem in Radio Frequency Identification (RFID) systems. Time efficiency is the top quality of service (QoS) metric in RFID tag identification. Traditional tag scanning approaches suffer from low time efficiency because they need to transmit tag IDs that are usually very long (e.g., 96 bits). In this paper, we investigate how to employ handheld readers to improve the time efficiency of tag identification and provide flexibility to scan tags on different purposes. A fast and flexible tag scanning mechanism called LOCK is proposed, which combines both the information and the replying slot index of a tag's response. In LOCK, tags transmit only short responses instead of tag IDs. Based on LOCK, we propose two novel tag scanning protocols that progressively add new techniques on top of one another to improve the time efficiency. Compared to the state-of-the-art solution in literature, our best protocol reduces scanning time by up to 53 percent.

Cloning attacks seriously impede the security of Radio-Frequency Identification (RFID) applications. In this paper, we tackle deterministic clone detection for anonymous RFID systems without tag identifiers (IDs) as a priori. Existing clone detection protocols either cannot apply to anonymous RFID systems due to necessitating the knowledge of tag IDs or achieve only probabilistic detection with a few clones tolerated. We propose two protocols, BASE and DeClone, toward fast and deterministic clone detection for large anonymous RFID systems. BASE leverages the observation that clone tags make tag cardinality exceed ID cardinality. DeClone is built on a recent finding that clone tags cause collisions that are hardly reconciled through re-arbitration. For DeClone to achieve detection certainty, we design breadth first tree traversal toward quickly verifying unreconciled collisions and hence the cloning attack. We validate their detection performance through analysis and simulation. The results show that BASE delivers faster detection for small systems while DeClone for large ones especially when clone ratio increases.

Data gathering is one of the most basic applications of wireless sensor networks. How to effectively preserve the energy of the nodes in order to extend the network lifetime is a challenging problem in data gathering. Currently, many researches focus on constructing a virtual backbone of the network by using minimum connected dominating sets. Each node in the network can transmit its data to the sink by the virtual backbone. However, the minimum connected dominating sets may result in unbalanced energy consumption among nodes, which shortens lifetime of the network and consequently limits their application in many fields. In this paper, we propose an energy-balanced connected dominating set distributed scheme (DGA-EBCDS) which prolongs the network lifetime by constructing an energy-balanced connected dominating set for data gathering. When constructing the virtual backbone in DGA-EBCDS, we prioritize selecting those nodes with higher energy and larger degree. This makes the energy consumption among nodes more balanced. Furthermore, the routing decision in DGA-EBCDS considers both the path length and the remaining energy of nodes on the path. This further prolongs the lifetime of nodes in the backbone and hence extends the lifetime of the whole network. We theoretically analyze the DGA-EBCDS algorithm and conduct extensive simulations to evaluate its performance. Simulation results show that DGA-EBCDS outperforms mr-CDS by prolonging the network lifetime by more than 50 percent.

Cognitive radio technique improves spectrum utilization by allowing secondary users (SUs) to opportunistically exploit the authorized spectrum of primary users (PUs) to transmit their data. In order to avoid colliding with PU, SUs often sense the channel before transmission. As many secondary users are mobile devices, how to preserve energy consumption of the secondary users is considered in this paper. According to a defined utility function, SU dynamically schedules its actions, i.e., sensing, transmission or sleeping. the utility function is optimized based on the reward and penalty of sleeping actions. Those sleeping actions obeying the rule will be rewarded and those opposite actions will be penalized. SU schedules its action of sensing and sleeping so as to reach a tradeoff between the minimum energy consumption and PU's protection. By maximizing the mean benefit, the proposed strategy exhibits a simple threshold-based structure. Simulation results show that the proposed scheme can greatly reduce energy cost and achieve similar PU collision rate as previous works, with only negligible throughput reduction.

In WiMAX mesh networks based on IEEE 802.16j, when transmission power of the base station (BS) and the number of radios and channels are settled, data rate at the subscriber (SS) is decided by the distance between the SS and its uplink relay station (RS). In this paper, we study the problem of deploying a minimum number of RSs to satisfy all SSs' distance requirements. Firstly, we translate it into a minimum clique partition problem, which is NP-complete. Based on SSs' neighbor information and location information, we then propose two heuristic algorithms based on clique partition, named as MAXDCP and GEOCP, respectively. Simulation results show that, compared with the state-of-the-art MIS and HS algorithms, MAXDCP uses 23.8% fewer relays than MIS with the same time complexity, and GEOCP uses 35% fewer relays than MIS in the same time and 18.5% fewer relays than HS in much less time.

Data gathering is one basic functional operation provided by wireless sensor networks. Most existing clustering protocols suffer from unbalanced energy consumption among nodes, which shortens the lifetime of the network and limits their application in many fields. In this paper, an energy-balanced dominating set based clustering scheme (EBDSC) is proposed to prolong the network lifetime by balancing energy consumption among nodes. In EBDSC, each node calculates the number of potential data gathering rounds it can afford when it acts as a cluster head. The node that can afford most rounds among its neighbors becomes a candidate cluster head. A normal node that is not a candidate head calculates the average number of candidate cluster heads that cover it and broadcasts the value. A candidate head finds the median of the values received from its neighboring normal nodes, and becomes a final cluster head with a probability inversely proportional to the median. Extensive simulations are conducted to compare the performance of EDBSC and a previous work ECDS. The results show that EBDSC outperforms ECDS by prolonging the network lifetime by at most 51.4% as well as guaranteeing full network coverage.

The RFID technology greatly improves efficiency of many applications including inventory control, object tracking, and supply chain management. In such applications, it is common that new objects are added into the system or existing objects are misplaced in wrong regions. When this happens, fast and complete identification of such tags is very important. We name this problem unknown tag identification, as these tags appear to be unknown by the reader(s) currently covering them. In this paper, we propose a series of protocols to identify unknown tags completely and fast. In these protocols, we develop several novel techniques to efficiently resolve collisions caused by known tags when identifying unknown tags, which greatly improve the time efficiency. To our knowledge, this is the first work that completely identify all the unknown tags with deterministic approaches. Simulation results show the superior performance of the proposed protocols: Compared with a baseline method which collects IDs of all the tags in the system, our best protocol reduces the execution time by 63% in average and by 85% at most.

In anisotropic wireless sensor networks, range-free multilateration-based localization (RFML) protocols severely suffer from large error in node-anchor distance estimations or the bad geometry of anchors involved in the localization process. In this paper, we propose selective multilateration (SM), a RFML protocol in which a node adaptively selects a subset of anchor nodes with accurate distance estimates and good geometric distribution to perform multilateration. We make two main contributions: (1) We exploit the locality property of per hop length (two nearby nodes share similar per hop length to a far anchor node) to estimate node-anchor distances. This induces smaller distance estimation error than previous approaches that use a unified average per hop length for all nodes. (2) We propose a method to heuristically select a subset of good anchor nodes that have small distance estimation errors and good geometry quality measured by geometric dilution of precision (GDOP) to perform multilateration. We also use a method which mines sub-hop resolution proximity between neighboring nodes to reduce error in distance estimates which further improves localization accuracy. Simulation results show that, compared with PDM, SM improves distance estimation accuracy by up to 45 percent. The localization accuracy in SM is improved by up to 45 percent and 27 percent in average. Furthermore, SM incurs much less communication and computational overhead than PDM does, making it more suitable for large scale WSNs.

Delay tolerant networks (DTNs) characterise a class of emerging networks that suffer from frequent and long-duration partitions. As the storage-carry-forward paradigm is adopted to transfer messages in DTNs, buffer management schemes greatly influence the performance of routing protocols when nodes have limited buffer space. From a network-wide viewpoint, the excessive increase of a single message's copies will exhaust nodes' buffer space, thus reduces the probability of other messages to be buffered and forwarded and leads substantial decrease in their delivery ratio. In this paper, inspired by the law of diminishing marginal utility in economics, we propose a buffer management scheme based on estimated status of messages, e.g., the total number of copies in the network and the dissemination speed of a message. When performing buffer replacement and scheduling, nodes use encounter histories to estimate status of messages and act accordingly: when buffer overflow occurs, messages that have larger estimated number of copies and faster dissemination speed are replaced prior to and forwarded posterior to other messages. Simulation results show that our buffer management scheme can improve delivery ratio and has relative lower overhead ratio compared with other buffer management schemes.

Explicit feedback based congestion control schemes can capture network congestion status more accurately than pure end-to-end schemes. However, some of such schemes require modifying IP header in order to achieve near optimal performance, which incurs complicated computation in routers as well as makes them difficult to deploy in real networks. In contrast, the VCP protocol achieves good performance by using the two existing ECN bits in the IP header for feedback, but its convergence speed is relatively low due to insufficient congestion feedback. In this paper, we propose VCP-BE, a protocol based on VCP and uses end-to-end bandwidth estimation to obtain high resolution congestion estimation. With the estimated available bandwidth and ECN feedback, VCP-BE adjusts the congestion window more precisely than VCP thus converges much faster. Simulation results show that VCP-BE outperforms VCP and MLCP, achieving high efficiency and reasonable fairness.

Distance estimation is a key issue in range-free localization algorithms for wireless sensor networks. Approaches that assume isotropy of networks, such as Dv-hop and Gradient, cannot obtain accurate distance estimations in anisotropic sensor networks thus are not applicable to such networks. The anisotropy of sensor networks comes from two aspects: uneven nodal distribution and irregularity of deployment region. Existing localization algorithms for anisotropic wireless sensor networks usually only deal with one of the two aspects. In this paper, we propose an anchor supervised distance estimation approach which can simultaneously cope with both of the two aspects. In this approach, an anchor node selects a “friendly” subset from all other anchor nodes to which its distance estimates are accurate and broadcasts the selection result to neighboring common nodes. The common nodes then use these friendly anchors to perform distance estimation. We analyze distance estimation accuracy of this approach through extensive simulations. The results show that, compared with Dv-hop, our proposed approach dramatically reduces distance estimation error in anisotropic wireless sensor networks with an average factor of 67%. Consequently, the localization error of Dv-hop is reduced by an average factor of 71% if enhanced with our distance estimation approach.

Wireless sensor networks (WSNs) deployed in hostile environments are vulnerable to clone attacks. In such attack, an adversary compromises a few nodes, replicates them, and inserts arbitrary number of replicas into the network. Consequently, the adversary can carry out many internal attacks. Previous solutions on detecting clone attacks have several drawbacks. First, some of them require a central control, which introduces several inherent limits. Second, some of them are deterministic and vulnerable to simple witness compromising attacks. Third, in some solutions the adversary can easily learn the critical witness nodes to start smart attacks and protect replicas from being detected. In this paper, we first show that in order to avoid existing drawbacks, replica-detection protocols must be non-deterministic and fully distributed (NDFD), and fulfill three security requirements on witness selection. To our knowledge, only one existing protocol, Randomized Multicast, is NDFD and fulfills the requirements, but it has very high communication overhead. Then, based on random walk, we propose two new NDFD protocols, RAndom WaLk (RAWL) and Table-assisted RAndom WaLk (TRAWL), which fulfill the requirements while having only moderate communication and memory overheads. The random walk strategy outperforms previous strategies because it distributes a core step, the witness selection, to every passed node of random walks, and then the adversary cannot easily find out the critical witness nodes. We theoretically analyze the required number of walk steps for ensuring detection. Our simulation results show that our protocols outperform an existing NDFD protocol with the lowest overheads in witness selection, and TRAWL even has lower memory overhead than that protocol. The communication overheads of our protocols are higher but are affordable considering their security benefits.

Existing localization algorithms for mobile sensor networks are usually based on the Sequential Monte Carlo (SMC) method. They either suffer from low sampling efficiency or require high beacon density to achieve high localization accuracy. Although papers can be found for solving the above problems separately, there is no solution which addresses both issues. In this paper, we propose an energy efficient algorithm, called WMCL, which can achieve both high sampling efficiency and high localization accuracy in various scenarios. In existing algorithms, a technique called bounding-box is used to improve the sampling efficiency by reducing the scope from which the candidate samples are selected. WMCL can further reduce the size of a sensor node's bounding-box by a factor of up to 87 percent and, consequently, improve the sampling efficiency by a factor of up to 95 percent. The improvement in sampling efficiency dramatically reduces the computational cost. Our algorithm uses the estimated position information of sensor nodes to improve localization accuracy. Compared with algorithms adopting similar methods, WMCL can achieve similar localization accuracy with less communication cost and computational cost. Our work has additional advantages. First, most existing SMC-based localization algorithms cannot be used in static sensor networks but WMCL can work well, even without the need of experimentally tuning parameters as required in existing algorithms like MSL*. Second, existing algorithms have low localization accuracy when nodes move very fast. We propose a new algorithm in which WMCL is iteratively executed with different assumptions on nodes' speed. The new algorithm dramatically improves localization accuracy when nodes move very fast. We have evaluated the performance of our algorithm both theoretically and through extensive simulations. We have also validated the performance results of our algorithm by implementing it in real deployed static sensor networks. To the best of our knowledge, we are the first to implement SMC-based localization algorithms for wireless sensor networks in real environment.

Recently with the emergence of mobile sensor networks, localization for such networks has gained much attention, and many localization algorithms have been proposed. Among them the Sequential Monte Carlo (SMC) based algorithms are very popular because of their simplicity and efficiency. However, most current SMC-based localization algorithms implicitly assume there is no attacker in the network, which may not be true in real applications. The attackers, if any, may send false information by themselves or through compromised nodes to disturb the localization. In this paper, we present the design and evaluation of a Secure Monte Carlo Localization algorithm, SecMCL. SecMCL provides authentication to messages and employs a new sampling method to defeat attacks. Simulation results show that SecMCL greatly improves the localization accuracy of existing SMC-based localization method when there are attacks. Also, compared with existing SMC localization method, SecMCL incurs no communication cost (in terms of number of messages) and achieves the same localization accuracy when there is no attack.

Localization is an essential problem in Wireless Sensor Networks (WSNs). Many localization algorithms have been proposed, but few efforts have been paid on theoretical analysis on the accuracy of these algorithms. Because it is naturally to formalize range-based localization problems as deterministic parameter estimation problems, for range-based localization algorithms Cramér-Rao Lower Bound (CRLB) has been used to lower bound the variance on the estimation of sensor's positions. However, few similar works have been done for range-free localization algorithms. In this paper, based on geometry properties, we theoretically analyze bounds on accuracy for Region-Based Localization (RBL) algorithms which can be classified as one type of range-free localization algorithms. We prove that if in a RBL algorithm, the deployment region R with the area size s is partitioned into k regions (they can be with any shape and any area size), the localization accuracy is bounded below by no matter how the algorithm partitions R. Although the lower bound is not theoretically tight, our simulation results show that the gap between this bound and achievable accuracy is very small. We conjecture a tighter lower bound when k is large enough. We also observe that in order to achieve high localization accuracy, partitioned regions should have nearly the same size. We give three examples with simulation results to show how the results can be used to set the values of the parameters, like k and the corresponding anchor/event number, in a RBL algorithm in order to achieve desired localization accuracy.

Many secure localization algorithms have been proposed. In these algorithms, collusion attack is usually considered as the strongest attack when evaluating their performance. Also, for ensuring correct localization under the collusion attack, a necessary number of normal beacons are needed and a lower bound on this number has been established (assuming the errors of distance measurements are ignorable). In this paper, we introduce pollution attack, a more powerful attack which can succeed even when the number of normal beacons is more than the lower bound. In this attack, victim node is misled to a special chosen location, which results in a confusion of compromised beacon with normal beacon. We propose a new metric to measure the vulnerability of a normal location reference set to pollution attack, and develop two algorithms to efficiently compute the value of the proposed metric. We also present a method to judge whether the output of the localization algorithm is credible under pollution attack. Simulation results show that the pollution attack can succeed with high probability.

Localization in mobile sensor networks is more challenging than in static sensor networks because mobility increases the uncertainty of nodes' positions. Most existing localization algorithms in mobile sensor networks use Sequential Monte Carlo (SMC) methods due to their simplicity in implementation. However, SMC methods are very time-consuming because they need to keep sampling and filtering until enough samples are obtained for representing the posterior distribution of a moving node's position. In this paper, we propose a localization algorithm that can reduce the computation cost of obtaining the samples and improve the location accuracy. A simple bounding-box method is used to reduce the scope of searching the candidate samples. Inaccurate position estimations of the common neighbor nodes is used to reduce the scope of finding the valid samples and thus improve the accuracy of the obtained location information. Our simulation results show that, comparing with existing algorithms, our algorithm can reduce the total computation cost and increase the location accuracy. In addition, our algorithm shows several other benefits: (1) it enables each determined node to know its maximum location error, (2) it achieves higher location accuracy under higher density of common nodes, and (3) even when there are only a few anchor nodes, most nodes can still get position estimations.