Exploiting big data knowledge on small devices will pave the way for building truly cognitive Internet of Things (IoT) systems. Although machine learning has led to great advancements for IoT-based data analytics, there remains a huge methodological gap for the deployment phase of trained machine learning models. For given resource-constrained platforms such as Microcontroller Units (MCUs), model choice and parametrization are typically performed based on heuristics or analytical models. However, these approaches are only able to provide rough estimates of the required system resources as they do not consider the interplay of hardware, compiler specific optimizations, and code dependencies. In this paper, we present the novel open source framework LIghtweight Machine learning for IoT Systems (LIMITS), which applies a platform-in-the-loop approach explicitly considering the actual compilation toolchain of the target IoT platform. LIMITS focuses on high level tasks such as experiment automation, platform-specific code generation, and sweet spot determination. The solid foundations of validated low-level model implementations are provided by the coupled well-established data analysis framework Waikato Environment for Knowledge Analysis (WEKA). We apply and validate LIMITS in two case studies focusing on cellular data rate prediction and radio-based vehicle classification, where we compare different learning models and real world IoT platforms with memory constraints from 16 kB to 4 MB and demonstrate its potential to catalyze the development of machine learning enabled IoT systems.
The Internet of Things (IoT) will be a main data generation infrastructure for achieving better system intelligence. This paper considers the design and implementation of a practical privacy-preserving collaborative learning scheme, in which a curious learning coordinator trains a better machine learning model based on the data samples contributed by a number of IoT objects, while the confidentiality of the raw forms of the training data is protected against the coordinator. Existing distributed machine learning and data encryption approaches incur significant computation and communication ove…
Lightweight Intrusion Detection in IoT via SHAP-Guided Feature Pruning and Knowledge-Distilled Kronecker Networks
LSIA Laboratory, Moroccan School of Engineering Sciences (EMSI)（摩洛哥工程科学学校LSIA实验室）；Laboratory of Research in Informatics (LaRI), Faculty of Sciences, Ibn Tofail University（伊本·泰菲勒大学信息研究实验室）；College of Computing, University Mohammed VI Polytechnic（穆莱·伊沙克六世理工学院计算机学院）
Recent literature suggests that the Internet of Things (IoT) scales much better in an Information-Centric Networking (ICN) model instead of the current host-centric Internet Protocol (IP) model. In particular, the Named Data Networking (NDN) project (one of the ICN architecture flavors) offers features exploitable by IoT applications, such as stateful forwarding, in- network caching, and built-in assurance of data provenance. Though NDN-based IoT frameworks have been proposed, none have adequately and holistically addressed concerns related to secure onboarding and routing. Additionally, emerg…
Link-Aware Energy-Frugal Continual Learning for Fault Detection in IoT Networks
Department of Electronic Systems, Aalborg University（电子系统系，奥尔堡大学）；Department of Electrical and Computer Engineering, Aarhus University（电气与计算机工程系，阿arhus大学）
The emerging blockchain protocols provide a decentralized architecture that is suitable of supporting Internet of Things (IoT) interactions. However, keeping a local copy of the blockchain ledger is infeasible for low-power and memory-constrained devices. For this reason, they are equipped with lightweight software implementations that only download the useful data structures, e.g. state of accounts, from the blockchain network, when they are updated. In this paper, we consider and analyze a novel scheme, implemented by the nodes of the blockchain network, which aggregates the blockchain data …
The Internet of Things (IoT) will be a main data generation infrastructure for achieving better system intelligence. This paper considers the design and implementation of a practical privacy-preserving collaborative learning scheme, in which a curious learning coordinator trains a better machine learning model based on the data samples contributed by a number of IoT objects, while the confidentiality of the raw forms of the training data is protected against the coordinator. Existing distributed machine learning and data encryption approaches incur significant computation and communication ove…
The Internet of Things, also known as the IoT, refers to the billions of devices around the world that are now connected to the Internet, collecting and sharing data. The amount of data collected through IoT sensors must be completely securely controlled. To protect the information collected by IoT sensors, a lightweight method called Discover the Flooding Attack-RPL (DFA-RPL) has been proposed. The proposed DFA-RPL method identifies intrusive nodes in several steps to exclude them from continuing routing operations. Thus, in the DFA-RPL method, it first builds a cluster and selects the most a…
Information Centric Networking is a new networking paradigm that treats content as first class entity. It provides content to users without regards to the current location of the content. The publish/subscribe systems have gained popularity in Internet. Pub/sub systems dismisses the need for users to request every content of their interest. Instead, the content is supplied to interested users (subscribers) as and when it is published. CCN/NDN are popular ICN proposals widely accepted in the ICN community however, they do not provide an efficient pub/sub mechanism. COPSS enhances CCN/NDN with a…
Home automation Internet of Things (IoT) systems have recently become a target for several types of attacks. In this paper, we present an authentication and key agreement protocol for a home automation network based on the ZigBee standard, which connects together a central controller and several end devices. Our scheme performs mutual authentication between end devices and the controller, which is followed by device-to-device communication. The scheme achieves confidentiality, message integrity, anonymity, unlinkability, forward and backward secrecy, and availability. Our scheme uses only simp…
Internet of Things (IoT) is considered as a key enabler of health informatics. IoT-enabled devices are used for in-hospital and in-home patient monitoring to collect and transfer biomedical data pertaining to blood pressure, electrocardiography (ECG), blood sugar levels, body temperature, etc. Among these devices, wearables have found their presence in a wide range of healthcare applications. These devices generate data in real-time and transmit them to nearby gateways and remote servers for processing and visualization. The data transmitted by these devices are vulnerable to a range of advers…
Executing deep neural networks for inference on the server-class or cloud backend based on data generated at the edge of Internet of Things is desirable due primarily to the limited compute power of edge devices and the need to protect the confidentiality of the inference neural networks. However, such a remote inference scheme incurs concerns regarding the privacy of the inference data transmitted by the edge devices to the curious backend. This paper presents a lightweight and unobtrusive approach to obfuscate the inference data at the edge devices. It is lightweight in that the edge device …
IoT has enabled the rapid growth of smart remote healthcare applications. These IoT-based remote healthcare applications deliver fast and preventive medical services to patients at risk or with chronic diseases. However, ensuring data security and patient privacy while exchanging sensitive medical data among medical IoT devices is still a significant concern in remote healthcare applications. Altered or corrupted medical data may cause wrong treatment and create grave health issues for patients. Moreover, current remote medical applications' efficiency and response time need to be addressed an…
Edge/Fog computing is a novel computing paradigm that provides resource-limited Internet of Things (IoT) devices with scalable computing and storage resources. Compared to cloud computing, edge/fog servers have fewer resources, but they can be accessed with higher bandwidth and less communication latency. Thus, integrating edge/fog and cloud infrastructures can support the execution of diverse latency-sensitive and computation-intensive IoT applications. Although some frameworks attempt to provide such integration, there are still several challenges to be addressed, such as dynamic scheduling …
Development, deployment and maintenance of networked software has been revolutionized by DevOps, which have become essential to boost system software quality and to enable agile evolution. Meanwhile the Internet of Things (IoT) connects more and more devices which are not covered by DevOps tools: low-power, microcontroller-based devices. In this paper, we contribute to bridge this gap by designing Femto-Containers, a new architecture which enables containerization, virtualization and secure deployment of software modules embedded on microcontrollers over low-power networks. As proof-of-concept…
One of the key technologies for future IoT/M2M systems are low power wide area networks, which are designed to support a massive number of low-end devices often in the unlicensed shared spectrum using random access protocols. However these usually operate without centralised control and since Automatic Repeat request and acknowledgement mechanisms are not very effective due to the strict duty cycles limits and high interference in the shared bands, many packets are lost from collisions. In this paper we analyse a recently proposed application layer coding scheme, which aims to recover lost pac…
The devices forming the Internet-of-Things (IoT) networks need to be re-programmed over-the-air, so that new features are added, software bugs or security vulnerabilities are resolved and their applications can be re-purposed. The limitations of IoT devices, such as installation in locations with limited physical access, resource-constraint nature, large scale and high heterogeneity, should be taken into consideration for designing an efficient and reliable pipeline for over-the-air programming (OTAP). In this work, we present a survey of OTAP techniques, which can be applied to IoT networks. …
With the ever growing Internet of Things (IoT) market, ledger systems are facing new challenges to efficiently store and secure enormous customer records collected by the IoT devices. The authenticity, availability, and integrity of these records are critically important for both business providers and customers. In this paper, we describe DLedger, a lightweight and resilient distributed ledger system. Instead of a single chain of blocks, DLedger builds the ledger over a directed acyclic graph (DAG), so that its operations can tolerate network partition and intermittent connectivity. Instead o…
Internet of Things (IoT) is the new industrial slogan for connecting intelligent and unintelligent devices to the web. The problem of security of data transfer, interoperability of different proposed methodologies, the ubiquity of Wi-Fi and the development of low power consuming MCUs has broadened the search for the best alternative technology for IoT in the oil and gas sector. This paper focus on the communication method for IoT devices to determine the level of functionality and the efficiency of interfacing the new MOD-WIFI-ESP8266-DEV Wi-Fi unit based on the IEEE 802.11 standard with MSP43…
Data transmission accounts for significant energy consumption in wireless sensor networks where streaming data is generatedby the sensors. This impedes their use in many settings, including livestock monitoring over large pastures (which formsour target application). We present Ambrosia, a lightweight protocol that utilizes a window-based timeseries forecastingmechanism for data reduction. Ambrosia employs a configurable error threshold to ensure that the accuracy of end applicationsis unaffected by the data transfer reduction. Experimental evaluations using LoRa and BLE on a real livestock mo…
