arXiv subjects

Houbing Song

Publications and source records attributed to Houbing Song.

47 records · Page 3Linked to original sources

arXiv2021

Machine Learning for the Detection and Identification of Internet of Things (IoT) Devices: A Survey

The Internet of Things (IoT) is becoming an indispensable part of everyday life, enabling a variety of emerging services and applications. However, the presence of rogue IoT devices has exposed the IoT to untold risks with severe consequences. The first step in securing the IoT is detecting rogue IoT devices and identifying legitimate ones. Conventional approaches use cryptographic mechanisms to authenticate and verify legitimate devices' identities. However, cryptographic protocols are not available in many systems. Meanwhile, these methods are less effective when legitimate devices can be exploited or encryption keys are disclosed. Therefore, non-cryptographic IoT device identification and rogue device detection become efficient solutions to secure existing systems and will provide additional protection to systems with cryptographic protocols. Non-cryptographic approaches require more effort and are not yet adequately investigated. In this paper, we provide a comprehensive survey on machine learning technologies for the identification of IoT devices along with the detection of compromised or falsified ones from the viewpoint of passive surveillance agents or network operators. We classify the IoT device identification and detection into four categories: device-specific pattern recognition, Deep Learning enabled device identification, unsupervised device identification, and abnormal device detection. Meanwhile, we discuss various ML-related enabling technologies for this purpose. These enabling technologies include learning algorithms, feature engineering on network traffic traces and wireless signals, continual learning, and abnormality detection.

cs.CR↗

arXiv2021

geoGAT: Graph Model Based on Attention Mechanism for Geographic Text Classification

In the area of geographic information processing. There are few researches on geographic text classification. However, the application of this task in Chinese is relatively rare. In our work, we intend to implement a method to extract text containing geographical entities from a large number of network text. The geographic information in these texts is of great practical significance to transportation, urban and rural planning, disaster relief and other fields. We use the method of graph convolutional neural network with attention mechanism to achieve this function. Graph attention networks is an improvement of graph convolutional neural networks. Compared with GCN, the advantage of GAT is that the attention mechanism is proposed to weight the sum of the characteristics of adjacent nodes. In addition, We construct a Chinese dataset containing geographical classification from multiple datasets of Chinese text classification. The Macro-F Score of the geoGAT we used reached 95\% on the new Chinese dataset.

cs.CL↗

arXiv2020

Distant Domain Transfer Learning for Medical Imaging

Medical image processing is one of the most important topics in the field of the Internet of Medical Things (IoMT). Recently, deep learning methods have carried out state-of-the-art performances on medical image tasks. However, conventional deep learning have two main drawbacks: 1) insufficient training data and 2) the domain mismatch between the training data and the testing data. In this paper, we propose a distant domain transfer learning (DDTL) method for medical image classification. Moreover, we apply our methods to a recent issue (Coronavirus diagnose). Several current studies indicate that lung Computed Tomography (CT) images can be used for a fast and accurate COVID-19 diagnosis. However, the well-labeled training data cannot be easily accessed due to the novelty of the disease and a number of privacy policies. Moreover, the proposed method has two components: Reduced-size Unet Segmentation model and Distant Feature Fusion (DFF) classification model. It is related to a not well-investigated but important transfer learning problem, termed Distant Domain Transfer Learning (DDTL). DDTL aims to make efficient transfers even when the domains or the tasks are entirely different. In this study, we develop a DDTL model for COVID-19 diagnose using unlabeled Office-31, Catech-256, and chest X-ray image data sets as the source data, and a small set of COVID-19 lung CT as the target data. The main contributions of this study: 1) the proposed method benefits from unlabeled data collected from distant domains which can be easily accessed, 2) it can effectively handle the distribution shift between the training data and the testing data, 3) it has achieved 96\% classification accuracy, which is 13\% higher classification accuracy than "non-transfer" algorithms, and 8\% higher than existing transfer and distant transfer algorithms.

eess.IV↗

arXiv2020

Counter-Unmanned Aircraft System(s) (C-UAS): State of the Art, Challenges and Future Trends

Unmanned aircraft systems (UAS), or unmanned aerial vehicles (UAVs), often referred to as drones, have been experiencing healthy growth in the United States and around the world. The positive uses of UAS have the potential to save lives, increase safety and efficiency, and enable more effective science and engineering research. However, UAS are subject to threats stemming from increasing reliance on computer and communication technologies, which place public safety, national security, and individual privacy at risk. To promote safe, secure and privacy-respecting UAS operations, there is an urgent need for innovative technologies for detecting, tracking, identifying and mitigating UAS. A Counter-UAS (C-UAS) system is defined as a system or device capable of lawfully and safely disabling, disrupting, or seizing control of an unmanned aircraft or unmanned aircraft system. Over the past 5 years, significant research efforts have been made to detect, and mitigate UAS: detection technologies are based on acoustic, vision, passive radio frequency, radar, and data fusion; and mitigation technologies include physical capture or jamming. In this paper, we provide a comprehensive survey of existing literature in the area of C-UAS, identify the challenges in countering unauthorized or unsafe UAS, and evaluate the trends of detection and mitigation for protecting against UAS-based threats. The objective of this survey paper is to present a systematic introduction of C-UAS technologies, thus fostering a research community committed to the safe integration of UAS into the airspace system.

eess.SP↗

arXiv2020

Zero-Bias Deep Learning for Accurate Identification of Internet of Things (IoT) Devices

The Internet of Things (IoT) provides applications and services that would otherwise not be possible. However, the open nature of IoT make it vulnerable to cybersecurity threats. Especially, identity spoofing attacks, where an adversary passively listens to existing radio communications and then mimic the identity of legitimate devices to conduct malicious activities. Existing solutions employ cryptographic signatures to verify the trustworthiness of received information. In prevalent IoT, secret keys for cryptography can potentially be disclosed and disable the verification mechanism. Non-cryptographic device verification is needed to ensure trustworthy IoT. In this paper, we propose an enhanced deep learning framework for IoT device identification using physical layer signals. Specifically, we enable our framework to report unseen IoT devices and introduce the zero-bias layer to deep neural networks to increase robustness and interpretability. We have evaluated the effectiveness of the proposed framework using real data from ADS-B (Automatic Dependent Surveillance-Broadcast), an application of IoT in aviation. The proposed framework has the potential to be applied to accurate identification of IoT devices in a variety of IoT applications and services. Codes and data are available in IEEE Dataport.

cs.LG↗

arXiv2019

Security of the Internet of Things: Vulnerabilities, Attacks and Countermeasures

Wireless Sensor Networks (WSNs) constitute one of the most promising third-millennium technologies and have a wide range of applications in our surrounding environment. The reason behind the vast adoption of WSNs in various applications is that they have tremendously appealing features, e.g., low production cost, low installation cost, unattended network operation, autonomous and longtime operation. WSNs have started to merge with the Internet of Things (IoT) through the introduction of Internet access capability in sensor nodes and sensing ability in Internet-connected devices. Thereby, the IoT is providing access to huge amount of data, collected by the WSNs, over the Internet. However, owing to the absence of a physical line-of-defense, i.e. there is no dedicated infrastructure such as gateways to watch and observe the flowing information in the network, security of WSNs along with IoT is of a big concern to the scientific community. Besides, recent integration and collaboration of WSNs with IoT will open new challenges and problems in terms of security. Hence, this would be a nightmare for the individuals using these systems as well as the security administrators who are managing those networks. Therefore, a detailed review of security attacks towards WSNs and IoT, along with the techniques for prevention, detection, and mitigation of those attacks are provided in this paper. In this text, attacks are categorized and treated into mainly two parts, most or all types of attacks towards WSNs and IoT are investigated under that umbrella: "Passive Attacks" and "Active Attacks". Understanding these attacks and their associated defense mechanisms will help to pave a secure path towards the proliferation and public acceptance of IoT technology.

cs.CR↗

arXiv2019

SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images

High-resolution aerial images have a wide range of applications, such as military exploration, and urban planning. Semantic segmentation is a fundamental method extensively used in the analysis of high-resolution aerial images. However, the ground objects in high-resolution aerial images have the characteristics of inconsistent scales, and this feature usually leads to unexpected predictions. To tackle this issue, we propose a novel scale-aware module (SAM). In SAM, we employ the re-sampling method aimed to make pixels adjust their positions to fit the ground objects with different scales, and it implicitly introduces spatial attention by employing a re-sampling map as the weighted map. As a result, the network with the proposed module named scale-aware network (SANet) has a stronger ability to distinguish the ground objects with inconsistent scale. Other than this, our proposed modules can easily embed in most of the existing network to improve their performance. We evaluate our modules on the International Society for Photogrammetry and Remote Sensing Vaihingen Dataset, and the experimental results and comprehensive analysis demonstrate the effectiveness of our proposed module.

cs.CV↗

arXiv2019

ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Images

Building footprint extraction from high-resolution aerial images is always an essential part of urban dynamic monitoring, planning and management. It has also been a challenging task in remote sensing research. In recent years, deep neural networks have made great achievement in improving accuracy of building extraction from remote sensing imagery. However, most of existing approaches usually require large amount of parameters and floating point operations for high accuracy, it leads to high memory consumption and low inference speed which are harmful to research. In this paper, we proposed a novel efficient network named ESFNet which employs separable factorized residual block and utilizes the dilated convolutions, aiming to preserve slight accuracy loss with low computational cost and memory consumption. Our ESFNet obtains a better trade-off between accuracy and efficiency, it can run at over 100 FPS on single Tesla V100, requires 6x fewer FLOPs and has 18x fewer parameters than state-of-the-art real-time architecture ERFNet while preserving similar accuracy without any additional context module, post-processing and pre-trained scheme. We evaluated our networks on WHU Building Dataset and compared it with other state-of-the-art architectures. The result and comprehensive analysis show that our networks are benefit for efficient remote sensing researches, and the idea can be further extended to other areas. The code is public available at: https://github.com/mrluin/ESFNet-Pytorch

cs.CV↗

arXiv2018

Social-Feature Enabled Communications among Devices towards Smart IoT Community

Future IoT is expected to get ubiquitous connection and access in a global scale. In the meantime, with the empowered communications capability for IoT devices, IoT will evolve to be highly autonomous, even under the help from infrastructure, and thus will gradually establish the smart IoT community. One of the major challenges imposed on the smart IoT communities is the socialization of IoT communications, because massive IoT accesses make centralized control very hard and also face the shortage of spectrum resources. Towards these issues, we in this article first present the overview and discussions on social features affecting connections among devices. Then, we motivate studies on the statistical characteristics of social features for connections among devices towards smart IoT. We further propose the queuing model under unified asymptotic analyses framework to characterize the statistical social features, with emphases on typical social metrics such as credit, reputation, centrality, etc. How to apply these features for network optimization is further suggested. Finally, we share our opinion on the open problems of social-aware design towards future smart IoT.

cs.NI↗

arXiv2018

Communication and Synchronization of Distributed Medical Models: Design, Development, and Performance Analysis

Model-based development is a widely-used method to describe complex systems that enables the rapid prototyping. Advances in the science of distributed systems has led to the development of large scale statechart models which are distributed among multiple locations. Taking medicine for example, models of best-practice guidelines during rural ambulance transport are distributed across hospital settings from a rural hospital, to an ambulance, to a central tertiary hospital. Unfortunately, these medical models require continuous and real-time communication across individual medical models in physically distributed treatment locations which provides vital assistance to the clinicians and physicians. This makes it necessary to offer methods for model-driven communication and synchronization in a distributed environment. In this paper, we describe ModelSink, a middleware to address the problem of communication and synchronization of heterogeneous distributed models. Being motivated by the synchronization requirements during emergency ambulance transport, we use medical best-practice models as a case study to illustrate the notion of distributed models. Through ModelSink, we achieve an efficient communication architecture, open-loop-safe protocol, and queuing and mapping mechanisms compliant with the semantics of statechart-based model-driven development. We evaluated the performance of ModelSink on distributed sets of medical models that we have developed to assess how ModelSink performs in various loads. Our work is intended to assist clinicians, EMT, and medical staff to prevent unintended deviations from medical best practices, and overcome connectivity and coordination challenges that exist in a distributed hospital network. Our practice suggests that there are in fact additional potential domains beyond medicine where our middleware can provide needed utility.

cs.SE↗

arXiv2017

Towards Physiology-Aware DASH: Bandwidth-Compliant Prioritized Clinical Multimedia Communication in Ambulances

The ultimate objective of medical cyber-physical systems is to enhance the safety and effectiveness of patient care. To ensure safe and effective care during emergency patient transfer from rural areas to center tertiary hospitals, reliable and real-time communication is essential. Unfortunately, real-time monitoring of patients involves transmission of various clinical multimedia data including videos, medical images, and vital signs, which requires use of mobile network with high-fidelity communication bandwidth. However, the wireless networks along the roads in rural areas range from 4G to 2G to low speed satellite links, which poses a significant challenge to transmit critical patient information. In this paper, we present a bandwidth-compliant criticality-aware system for transmission of massive clinical multimedia data adaptive to varying bandwidths during patient transport. Model-based clinical automata are used to determine the criticality of clinical multimedia data. We borrow concepts from DASH, and propose physiology-aware adaptation techniques to transmit more critical clinical data with higher fidelity in response to changes in disease, clinical states, and bandwidth condition. In collaboration with Carle's ambulance service center, we develop a bandwidth profiler, and use it as proof of concept to support our experiments. Our preliminary evaluation results show that our solutions ensure that most critical patient's clinical data are communicated with higher fidelity.

cs.NI↗