Resource-constrained IoT Devices Research Articles

Tiny, Always-on, and Fragile: Bias Propagation through Design Choices in On-device Machine Learning Workflows

Billions of distributed, heterogeneous, and resource constrained IoT devices deploy on-device machine learning (ML) for private, fast, and offline inference on personal data. On-device ML is highly context dependent and sensitive to user, usage, hardware, and environment attributes. This sensitivity and the propensity toward bias in ML makes it important to study bias in on-device settings. Our study is one of the first investigations of bias in this emerging domain and lays important foundations for building fairer on-device ML. We apply a software engineering lens, investigating the propagation of bias through design choices in on-device ML workflows. We first identify reliability bias as a source of unfairness and propose a measure to quantify it. We then conduct empirical experiments for a keyword spotting task to show how complex and interacting technical design choices amplify and propagate reliability bias . Our results validate that design choices made during model training, like the sample rate and input feature type, and choices made to optimize models, like light-weight architectures, the pruning learning rate, and pruning sparsity, can result in disparate predictive performance across male and female groups. Based on our findings, we suggest low effort strategies for engineers to mitigate bias in on-device ML.

Modified lightweight GIFT cipher for security enhancement in resource-constrained IoT devices

Modified lightweight GIFT cipher for security enhancement in resource-constrained IoT devices

Cross-Layer Federated Learning for Lightweight IoT Intrusion Detection Systems.

With the proliferation of IoT devices, ensuring the security and privacy of these devices and their associated data has become a critical challenge. In this paper, we propose a federated sampling and lightweight intrusion-detection system for IoT networks that use K-meansfor sampling network traffic and identifying anomalies in a semi-supervised way. The system is designed to preserve data privacy by performing local clustering on each device and sharing only summary statistics with a central aggregator. The proposed system is particularly suitable for resource-constrained IoT devices such as sensors with limited computational and storage capabilities. We evaluate the system's performance using the publicly available NSL-KDD dataset. Our experiments and simulations demonstrate the effectiveness and efficiency of the proposed intrusion-detection system, highlighting the trade-offs between precision and recall when sharing statistics between workers and the coordinator. Notably, our experiments show that the proposed federated IDS can increase the true-positive rate up to 10% when the workers and the coordinator collaborate.

Modified Rijndael Algorithm for Resource-Constrained IoT-Based Wireless Sensor Networks

INTRODUCTION: IoT devices are small, have limited battery and computing capabilities, and cannot tolerate complex encryption. OBJECTIVES: Many encryption algorithms struggle to strike a balance between security and complexity. Increasing the level of security necessitates increasing complexity, which leads to higher encryption and decryption times. This research aims to provide a novel encryption method, Modified Rijndael Algorithm that balances security and complexity. METHODS: The classic Rijndael encryption technique has been modified to make it lighter and more secure, suitable for resource-constrained IoT devices. RESULTS: These modifications include adding the novel pre-processing step SISA-Crossover based on the two-point crossover operation of genetic algorithms, removing the Sub Byte step, changing the shift column phase, and decreasing the rounds. CONCLUSION: The proposed technique provides speed and higher security in encryption and decryption, increasing efficiency and randomness while reducing encryption and decryption times by 21.06% and CPU consumption by 13.2% compared to the traditional method.

Heterogeneous Sensor Data Acquisition and Federated Learning for Resource Constrained IoT Devices—A Validation

This paper focused on applying federated learning to process heterogeneous sensor data in a fog computing-enabled smart home environment. The fusion of sensor data from vision sensor, digital ambient sensor and passive infrared sensor is done in a distributed manner and the data processing using federated learning on Raspberry Pi edge nodes. The system uses edge nodes to train the respective machine learning models using federated learning without sending data to a centralized server. Instead, results from the training on multiple edge nodes are aggregated at the central node to produce a final machine-learning model. Each edge node deploys the aggregated model to recognize the subjects in the smart home environment and trigger an alert in case unknown subjects are identified. Linear regression model for temperature prediction and logistic regression model for humidity prediction using the ambient parameters are also trained in a federated way on the same edge nodes. The developed system uses the federated learning Flower framework for training the models. The obtained validation accuracy was 66% for the machine learning models that were built on the resource constraint server and edge clients through the federated learning. The developed system can be used in environments where communication bandwidth is limited, or data privacy concerns exist.

DC-PUF: Machine learning-resistant PUF-based authentication protocol using dependency chain for resource-constraint IoT devices

The Physical Unclonable Function (PUF) is a hardware block which exploits the inherent process variations introduced during manufacturing to assign a unique fingerprint for each physical entity. This feature enables a low-cost authentication mechanism for connected devices, which is easy to evaluate but hard to predict. In this paper, we develop a low-cost PUF-based authentication mechanism called DC-PUF for resource-constrained IoT devices which can resist against machine-learning attacks. A new strategy known as the dependency chain (DC) is employed by which the response in each clock is dependent not only on the current challenge but also on the previous responses. This mechanism which takes advantage of both randomization and dependency chain hardens the ability to clone or predict the PUF instance by obfuscating the correlation between challenge-response pairs. Moreover, we propose a CNN-based attack scenario by which the existing PUF structures cannot resist while yielding more than 95% of prediction accuracy. The experimental results signify that unlike the existing PUFs, more than 58% of prediction accuracy cannot be reached when a sophisticated CNN-based attack is conducted to the DC-PUF, even with a large data-set. Also, the False-Negative rate is about 1%, in average, for three-bit mismatches in the receiving response in the presence of channel variations, whereas the False-Positive rate remains zero. Moreover, the proposed DC-PUF incurs lower hardware complexity and reasonable reliability and randomness compared to the existing PUF structures.

Obfuscated Memory Malware Detection in Resource-Constrained IoT Devices for Smart City Applications.

Obfuscated Memory Malware (OMM) presents significant threats to interconnected systems, including smart city applications, for its ability to evade detection through concealment tactics. Existing OMM detection methods primarily focus on binary detection. Their multiclass versions consider a few families only and, thereby, fail to detect much existing and emerging malware. Moreover, their large memory size makes them unsuitable to be executed in resource-constrained embedded/IoT devices. To address this problem, in this paper, we propose a multiclass but lightweight malware detection method capable of identifying recent malware and is suitable to execute in embedded devices. For this, the method considers a hybrid model by combining the feature-learning capabilities of convolutional neural networks with the temporal modeling advantage of bidirectional long short-term memory. The proposed architecture exhibits compact size and fast processing speed, making it suitable for deployment in IoT devices that constitute the major components of smart city systems. Extensive experiments with the recent CIC-Malmem-2022 OMM dataset demonstrate that our method outperforms other machine learning-based models proposed in the literature in both detecting OMM and identifying specific attack types. Our proposed method thus offers a robust yet compact model executable in IoT devices for defending against obfuscated malware.

IoTSL: Toward Efficient Distributed Learning for Resource-Constrained Internet of Things

Recently proposed Split Learning (SL) is a promising distributed machine learning paradigm that enables machine learning without accessing the raw data of the clients. SL can be viewed as one specific type of serial federation learning. However, deploying SL on resource-constrained IoT devices still has some limitations, including high communication costs and catastrophic forgetting problems caused by imbalanced data distribution of devices. In this paper, we design and implement IoTSL, which is an efficient distributed learning framework for efficient cloudedge collaboration in IoT systems. IoTSL combines generative adversarial networks (GANs) and differential privacy techniques to train local data-based generators on participating devices, and generate data with privacy protection. On the one hand, IoTSL pre-trains the global model using the generative data, and then fine-tunes the model using the local data to lower the communication cost. On the other hand, the generated data is used to impute the missing classes of devices to alleviate the commonly seen catastrophic forgetting phenomenon. We use three common datasets to verify the proposed framework. Extensive experimental results show that compared to the conventional SL, IoTSL significantly reduces communication costs, and efficiently alleviates the catastrophic forgetting phenomenon.

Distributed and Efficient Slot Assignment–Alignment Protocol for Resource-Constrained Wireless IoT Devices

Distributed and Efficient Slot Assignment–Alignment Protocol for Resource-Constrained Wireless IoT Devices

Oscillator Selection Strategies to Optimize a Physically Unclonable Function for IoT Systems Security.

Physically unclonable functions avoid storing secret information in non-volatile memories and only generate a key when it is necessary for an application, rising as a promising solution for the authentication of resource-constrained IoT devices. However, the need to minimize the predictability of physically unclonable functions is evident. The main purpose of this work is to determine the optimal way to construct a physically unclonable function. To do this, a ring oscillator physically unclonable function based on comparing oscillators in pairs has been implemented in an FPGA. This analysis shows that the frequencies of the oscillators greatly vary depending on their position in the FPGA, especially between oscillators implemented in different types of slices. Furthermore, the influence of the chosen locations of the ring oscillators on the quality of the physically unclonable function has been analyzed and we propose five strategies to select the locations of the oscillators. Among the strategies proposed, two of them stand out for their high uniqueness, reproducibility, and identifiability, so they can be used for authentication purposes. Finally, we have analyzed the reproducibility for the best strategy facing voltage and temperature variations, showing that it remains stable in the studied range.

A Block Cipher for Resource-Constrained IoT Devices

A Block Cipher for Resource-Constrained IoT Devices

A resource efficient pseudo random number generator based on sawtooth maps for Internet of Things

AbstractThe strength of cryptographic keys rely on the random number generators (RNGs) to produce random seed values. Unfortunately there are not many RNGs options suitable for Internet of Things (IoTs) scenario, due to limited processing resources and bulk quantity of IoT data that needs to be secured. In this article, we studied sawtooth map which is a chaotic map. However, when implemented on a computer, the sawtooth map results on a non‐chaotic orbit due to the finite precision of computation. This can be avoided if we use the sawtooth map as the local map in a coupled map lattice (CML) system. We explore such coupled map systems for randomness through entropy and statistical analysis. Based on the results, we propose a lightweight hybrid pseudo random number generator (PRNG) based on sawtooth based CML system and SPONGENT hashing. The proposed PRNG is thoroughly tested against statistical attacks, entropy analysis, key space analysis and compared with existing state of the art solutions. The results provide evidence that the proposed PRNG produces random numbers that could produce sufficiently strong cryptographic keys for resource constrained IoT devices.

Multiobjective End-to-End Design Space Exploration of Parameterized DNN Accelerators

Deep neural network (DNN) hardware accelerators enable the execution of complex DNN inferences on resource-constrained IoT devices. Inference performance and energy figures depend on how the DNN layers are mapped into the accelerator and how the architecture of the accelerator fits the variety of layers’ shapes of the actual DNN. The mapping determines the execution order of the operations, both temporally and spatially. Thus, selecting the best mapping that allows fitting the DNN model to the specific accelerator is of paramount importance to meet the strong constraints imposed by resource-scarce IoT platforms. Although several mapping space exploration techniques have been proposed in the literature, they are focused on determining the best mapping for a given layer, for a given architecture, and for optimizing a single objective. This article largely extends the scope of the exploration by considering the huge design space spanned by mapping related and architectural parameters, considering all the layers of the DNN, and optimizing multiple objectives simultaneously. We present EPOCA, end-to-end Pareto optimization of DNN accelerators, whose goal is to determine the accelerator’s architecture and the mapping for each layer that optimizes end-to-end and in a multiobjective fashion a set of conflicting design criteria. We assess EPOCA on different DNN models on a parameterized hardware accelerator designed for IoT applications and compare them with a state-of-the-art mapping space explorer, considering the area, inference latency, and inference energy as optimization metrics. We show that the set of Pareto solutions found by EPOCA provides the designer with a range of choices from which to select the best tradeoff with respect to the specific application.

Security Implementation on IoT using CoAP and Elliptical Curve Cryptography

IoT devices typically encompass objects or devices equipped with software and internet connectivity, allowing them to collect data. They have limited processing power, memory, and storage. These limitations can make it difficult to secure these devices, as traditional security measures may not be practical. Implementing security for IoT devices can be challenging due to these characteristics, but several steps can be taken to mitigate these challenges. Elliptic Curve Cryptography (ECC) can secure resource constrained IoT devices by providing a more efficient method of encryption and authentication than traditional methods such as RSA. In this paper, we analyzed the lightweight cryptographic algorithm ECC for securing resource-constrained devices such as IoT and evaluated its performance compared to the RSA cryptosystem. The analysis result indicates that ECC is considered to provide stronger security than RSA for the same key length. The CoAP protocol is applied to devices with limited resources, and an examination of its impact is conducted, considering three key performance metrics: CPU usage, bandwidth efficiency, and message communication latency.

Ethical hacking for IoT: Security issues, challenges, solutions and recommendations

In recent years, attacks against various Internet-of-Things systems, networks, servers, devices, and applications witnessed a sharp increase, especially with the presence of 35.82 billion IoT devices since 2021; a number that could reach up to 75.44 billion by 2025. As a result, security-related attacks against the IoT domain are expected to increase further and their impact risks to seriously affect the underlying IoT systems, networks, devices, and applications. The adoption of standard security (counter) measures is not always effective, especially with the presence of resource-constrained IoT devices. Hence, there is a need to conduct penetration testing at the level of IoT systems. However, the main issue is the fact that IoT consists of a large variety of IoT devices, firmware, hardware, software, application/web-servers, networks, and communication protocols. Therefore, to reduce the effect of these attacks on IoT systems, periodic penetration testing and ethical hacking simulations are highly recommended at different levels (end-devices, infrastructure, and users) for IoT, and can be considered as a suitable solution. Therefore, the focus of this paper is to explain, analyze and assess both technical and non-technical aspects of security vulnerabilities within IoT systems via ethical hacking methods and tools. This would offer practical security solutions that can be adopted based on the assessed risks. This process can be considered as a simulated attack(s) with the goal of identifying any exploitable vulnerability or/and a security gap in any IoT entity (end devices, gateway, or servers) or firmware.

Certrust: An SDN-Based Framework for the Trust of Certificates against Crossfire Attacks in IoT Scenarios

The low-intensity attack flows used by Crossfire attacks are hard to distinguish from legitimate flows. Traditional methods to identify the malicious flows in Crossfire attacks are rerouting, which is based on statistics. In these existing mechanisms, the identification of malicious flows depends on the IP address. However, the IP address is easy to be changed by attacks. Compared with the IP address, the certificate is more challenging to be tampered with or forged. Moreover, the traffic trend in the network is towards encryption. The certificates are popularly utilized by IoT devices for authentication in encryption protocols. DTLShps proposed a new way to verify certificates for resource-constrained IoT devices by using the SDN controller. Based on DTLShps, the SDN controller can collect statistics on certificates. In this paper, we propose Certrust, a framework based on the trust of certificates, to mitigate the Crossfire attack by using SDN for IoT. Our goal is threefold. First, the trust model is built based on the Bayesian trust system with the statistics on the participation of certificates in each Crossfire attack. Moreover, the forgetting curve is utilized instead of the traditional decay method in the Bayesian trust system for achieving a moderate decay rate. Second, for detecting the Crossfire attack accurately, a method based on graph connectivity is proposed. Third, several trust-based routing principles are proposed to mitigate the Crossfire attack. These principles can also encourage users to use certificates in communication. The performance evaluation shows that Certrust is more effective in mitigating the Crossfire attack than the traditional rerouting schemes. Moreover, our trust model has a more appropriate decay rate than the traditional methods.

Efficient low-area, high-frequency hardware implementations of shadow lightweight block ciphers for resource-constrained IoT devices and sensor networks

Efficient low-area, high-frequency hardware implementations of shadow lightweight block ciphers for resource-constrained IoT devices and sensor networks

FPGA implementation of PUF based key generator for secure communication in IoT

Various security measures for IoT devices have been introduced in recent years. One of the improvements is through the addition of cryptographic hardware along with the central core processor. As IoT devices are resource-constrained, area and power-efficient solutions are needed. Every cryptographic algorithm has a key generator that provides proper keys to encrypt and decrypt the data. This paper focuses on improving the key generators using Physical Unclonable Functions (PUFs). Execution of NIST-STS randomness test and evaluation of crucial performance parameters is done for the generated bit-stream by proposed PUF design. The proposed design is also compared with three designs from the literature based on area and power consumption which are essential parameters for resource-constrained IoT devices. For proposed design number of LUTs, FFs and power consumption are decreased up to 80%, 76% and 67%, respectively, when implemented on Xilinx Artix-7 FPGAs.

Can Open and AI-Enabled 6G RAN Be Secured?

The forthcoming 6g network goes beyond a new and Open Radio Access Network (O-RAN), allowing increased flexibility and interoperability. Intelligent radio network orchestration will be integral in the 6G era in order to control the radio network for near-real-time and nonreal-time applications. O-RAN reaches the goal of network flexibility through AI-enabled functions, particularly with machine learning (ML) systems. Hence, the role of AI/ML is immense in the envisioned 6G paradigm. However, the alliance between O-RAN and AI/ML may also be a double-edged sword in 6G as their applicability for protecting or infringing security and privacy. Hyperconnected Internet of Everything data collection for 6G application services raises privacy concerns. Data privacy, location privacy, and identity privacy will all be compromised as a result of data theft involving resource-constrained IoT devices. In addition, the O-RAN architecture consists almost entirely of virtualization and software functionality, which expands the threat and attack surface of the network. The open and AI-enabled 6G radio network is therefore susceptible to hacking, attacks, and disruptions.

Attacks on Resource-Constrained IoT Devices and Security Solutions

An IoT is a complex system of interconnected electronic devices that exchange data over the network. Due to the sensitive nature of the data involved in this new technological paradigm, security measures must be taken with great care. Researchers can better understand the threats and weaknesses of the IoT if attacks are categorized to facilitate the development of a more robust defense system. This study discusses various attacks and statistical data related to IoT. These attacks are divided into two categories: physical and cyber-attacks. Based on the literature review, the authors found that social engineering and DoS are the most common attacks in the physical and cyber categories. This study demonstrates the security solutions inherent to securing the IoT environment. Cryptography, blockchain, software-defined networks, and machine learning techniques were reviewed. They also discussed steps that should be taken to make a safe IoT environment.