Spectre-Fed: Evolving Federated Edge Intelligence from FedEdge-ID to Robust-Private IoT Intrusion Detection via Hybrid Adversarial Training

Machine learning systems (MLSys) are emerging in the Internet of Things (IoT) to provision edge intelligence, which is paving our way towards the vision of ubiquitous intelligence. However, despite the maturity of machine learning systems and the IoT, we are facing severe challenges when integrating MLSys and IoT in practical context. For instance, many machine learning systems have been developed for large-scale production (e.g., cloud environments), but IoT introduces additional demands due to heterogeneous and resource-constrained devices and decentralized operation environment. To shed light on this convergence of MLSys and IoT, this paper analyzes the trade-offs by covering the latest developments (up to 2020) on scaling and distributing ML across cloud, edge, and IoT devices. We position machine learning systems as a component of the IoT, and edge intelligence as a socio-technical system. On the challenges of designing trustworthy edge intelligence, we advocate a holistic design approach that takes multi-stakeholder concerns, design requirements and trade-offs into consideration, and highlight the future research opportunities in edge intelligence.

The exponentially growing Internet of Things (IoT) devices produce gigantic amounts of data every day. To process this ample IoT data, traditional centralized processing methods are mostly used, which face significant latency, bandwidth, and privacy challenges. Federated Learning (FL), a distributed machine learning (ML) technique, has become a promising solution to address these challenges by integrating edge computing environments. Federated edge intelligence can improve model accuracy and data privacy, and reduce latency and bandwidth. This approach allows IoT networks to train ML models collaboratively without centralizing data. This improves efficiency and preserves privacy and security. This chapter presents the fundamentals of FL, its architectural aspects, and demonstrates how it helps to further improve edge intelligence in IoT environments. We also discuss how edge devices can learn and train models with the use of the FL method. Furthermore, we provide examples of practical application use case scenarios, showcasing how this framework enhances real-time decision-making capabilities even while addressing data privacy. Finally, our research aims to guide future scholars through identifying the challenges this architecture currently faces and the future research directions associated with FL-based edge intelligence for IoT.

With the development of Internet of things, more and more personal information needs to be collected in the process of applying Internet of things technology, which brings about the problem of data privacy protection. The algorithm proposed in this paper uses the differential privacy model to process the information network collected by the wireless sensor network terminal in the perception layer of the Internet of things and transmits it to the network layer to achieve the purpose of information protection. In order to reduce the added differential privacy noise, this paper firstly makes dynamic community discovery of the network graph, and adds more noise to the edge of nodes within the community. Then the hierarchical random graph model is used to represent the network graph, and the noise is added to the connection probability between the nodes in the graph, instead of adding noise to the edge directly. Considering the dynamic change of the information collected by the wireless sensor network, this paper proposes a time window partition and dynamic network community discovery algorithm, and publishes a purification map for each time window. Through hierarchical sampling, the time cost is reduced and the cumulative error is reduced, while the network structure characteristics of the time window are maintained as far as possible. Theoretical analysis and experiments show that the algorithm proposed in this paper can preserve the important network structure characteristics of the original graph under the premise of satisfying the differential privacy protection model.

As a new type of distributed machine learning technology, federated learning has shown great application potential in the Internet of things, health care, smart home, finance and other fields. Its core advantage is that it can conduct model training without centralized data, effectively reducing the cost of data transmission and storage, and avoiding the risk of privacy disclosure. However, with the wide application of Federated learning, the problems of data security and privacy protection are increasingly apparent, especially in the face of complex network attacks and data leakage risks. This paper deeply analyzes the basic principles and architecture of Federated learning, and discusses the possible privacy threats in data transmission, model updating and participating devices in detail. Combined with the existing security protection technologies, such as differential privacy, encryption algorithm and secure multi-party computing, this paper discusses how to effectively ensure the security of Federated learning. Finally, the article also looks forward to the future development trend of Federated learning in privacy protection, model optimization, computational efficiency and cross domain collaboration, aiming to provide theoretical support and practical guidance for the further development and application of this technology.

The Internet of Things (IoT) is an essential component of the digital age, particularly in ensuring reliable and efficient operations as well as the timely and precise recognition of anomalies within IoT systems. However, anomaly detection in time-series data—especially data collected by edge devices—poses several challenges, including concerns over data privacy and communication overhead. To address these issues, this research proposes a novel deep learning (DL)-based anomaly detection model capable of being trained in real-time on edge devices within an IoT environment. The framework ensures user privacy by enabling distributed edge devices to cooperatively train an anomaly recognition system. This study introduces a new, Intelligent Shark Smell Tuned Deep Isolation Forest (ISS-DIF), which effectively detects anomalies and identifies outliers in industrial IoT sensor data with high accuracy. The hybrid model isolates anomalies rather than profiling normal data, making it particularly suitable for identifying rare anomalies within large datasets. Industrial data are collected from real-world manufacturing environments using IoT edge devices. Following data collection, median filtering is applied to reduce noise, and min-max scaling is employed for data normalization. The ISS component allows for fine-tuning the hyperparameters of the Deep Isolation Forest (DIF) to optimize detection performance. The DIF model is tailored to enhance anomaly detection capabilities in sensor data from industrial IoT applications. For validation, 80% of the dataset was used for training, while the remaining 20% served as the test set. The results demonstrate that the proposed ISS-DIF framework achieved superior training accuracy of 99.30%, with precision of 97.89%, recall of 98.76%, and an F1-score of 97.21%, outperforming the testing metrics. This approach integrates real-time anomaly detection with the processing capabilities of edge devices, thereby improving IoT data analytics and providing a scalable, efficient solution that preserves privacy in irregularity recognition within IoT environments.

The Internet of Things (IoT) forms intelligent systems, such as smart cities and factories, to enhance productivity and provide revolutionary and automated services to end-users and organisations. An IoT ecosystem requires more dynamics and heterogeneity with advanced privacy preservation. Federated Learning (FL)addresses the challenge of maintaining data privacy using a privacy-preserving sharing mechanism instead of transmitting raw data. However, the latest cyber threats cause privacy and security breaches. This study systematically analyses federated learning-based privacy-preserving methods in IoT systems. A standard IoT architecture with possible privacy threats is illustrated. Also, Federated Learning schemes and their taxonomies are discussed in a privacy-preserving manner, with initial experiments proving the significance of FLbased privacy preservation in IoT environments. This finds acceptable noise addition in differential privacy by keeping higher testing accuracy in different settings to enhance privacy preservation of federated learning. Various Federated Learning schemes, challenges and future research directions are covered.

CardioDefense: Defending against adversarial attack in ECG classification with adversarial distillation training

Adversarial robust image processing in medical digital twin

We have witnessed an unprecedented public health crisis caused by the new coronavirus disease (COVID-19), which has severely affected medical institutions, our common lives, and social-economic activities. This crisis also reveals the brittleness of existing medical services, such as over-centralization of medical resources, the hysteresis of medical services digitalization, and weak security and privacy protection of medical data. The integration of the Internet of Medical Things (IoMT) and blockchain is expected to be a panacea to COVID-19 attributed to the ubiquitous presence and the perception of IoMT as well as the enhanced security and immutability of the blockchain. However, the synergy of IoMT and blockchain is also faced with challenges in privacy, latency, and context absence. The emerging edge intelligence technologies bring opportunities to tackle these issues. In this article, we present blockchain-empowered edge intelligence for IoMT in addressing the COVID-19 crisis. We first review IoMT, edge intelligence, and blockchain in addressing the COVID-19 pandemic. We then present an architecture of blockchain-empowered edge intelligence for IoMT after discussing the opportunities of integrating blockchain and edge intelligence. We next offer solutions to COVID-19 brought by blockchain-empowered edge intelligence from 1) monitoring and tracing COVID-19 pandemic origin, 2) traceable supply chain of injectable medicines and COVID-19 vaccines, and 3) telemedicine and remote healthcare services. Moreover, we also discuss the challenges and open issues in blockchain-empowered edge intelligence.

In response to the privacy leakage risks inherent in the big data processing of power user personas, propose a collaborative optimization‐based joint privacy protection mechanism for Differential Privacy (DP) and Secret Sharing (SS). This method reveals the inherent correlation between DP noise parameters and SS sharding strategy and designs an adaptive noise sharding mapping mechanism to achieve joint optimization of privacy protection and communication overhead. Based on this mechanism, a specific privacy protection scheme for power user personas is designed. Experimental results demonstrate that the DP + SS privacy protection method designed in this study achieves an accuracy rate of 93.14% on the MNIST dataset and maintains an accuracy rate of 92.06% across multiple datasets, indicating that the scheme effectively quantifies the level of privacy protection. The privacy protection level of the scheme is quantitatively defined through differential privacy budget ε ∈ [0.11,0.15], secret sharing ( k = 3, n = 5) threshold mechanism, and privacy leakage probability δ = 10 −5 . The privacy budget is dynamically allocated through the correlation between differential privacy noise variance and the minimum reconstruction threshold of secret sharing, ensuring that privacy risks are controllable and quantifiable. At the same time, the average training time for servers is about 186.4 s, which refers to the total end‐to‐end training time in a four‐server cluster environment. Compared with a single server encryption scheme, the efficiency is improved by 48.6%. The communication overhead has increased to 10.6GB, which is the total chip transmission overhead per 10,000 users. However, the calculation stability can be maintained through load balancing, indicating that the scheme has certain feasibility. The aforementioned research results not only provide a viable applied cryptographic technology solution for privacy protection in power big data but also offer new insights into balancing privacy protection strength and data availability. More importantly, the joint privacy protection mechanism proposed by the research institute can serve as a fundamental enabling technology for the infrastructure of a secure smart grid, providing quantifiable and trustworthy privacy and security guarantees for advanced data‐driven applications such as precise load prediction, demand‐side response, and collaborative optimization of distributed energy, thereby supporting the reliable and intelligent development of the smart grid.

With the extensive deployment and application of the Internet of Things (IoT), 5G and 6G technologies and edge intelligence, the volume of data generated by IoT and the number of intelligence applications derived from these data are rapidly growing. However, the absence of effective mechanisms to safeguard the vast data generated by IoT, along with the security and privacy of edge intelligence applications, hinders their further development and adoption. In recent years, Trusted Execution Environment (TEE) has emerged as a promising technology for securing cloud data storage and cloud processing, demonstrating significant potential for ensuring data and application confidentiality in more scenarios. Nevertheless, applying TEE technology to enhance security in IoT and edge intelligence scenarios still presents several challenges. This paper investigates the technical challenges faced by current TEE solutions, such as performance overhead and I/O security issues, in the context of the resource constraints and data mobility that are inherent to IoT and edge intelligence applications. Using Intel Software Guard Extensions (SGX) technology as a case study, this paper validates these challenges through extensive experiments. The results provide critical assessments and analyses essential for advancing the development and usage of TEE in IoT and edge intelligence scenarios.

Privacy preserving Internet of Things: From privacy techniques to a blueprint architecture and efficient implementation

The successful emergence of deep learning (DL) in wireless system applications has raised concerns about new security-related challenges. One such security challenge is adversarial attacks. Although there has been much work demonstrating the susceptibility of DL-based classification tasks to adversarial attacks, regression-based problems in the context of a wireless system have not been studied so far from an attack perspective. The aim of this paper is twofold: (i) we consider a regression problem in a wireless setting and show that adversarial attacks can break the DL-based approach and (ii) we analyze the effectiveness of adversarial training as a defensive technique in adversarial settings and show that the robustness of DL-based wireless system against attacks improves significantly. Specifically, the wireless application considered in this paper is the DL-based power allocation in the downlink of a multicell massive multi-input-multi-output system, where the goal of the attack is to yield an infeasible solution by the DL model. We extend the gradient-based adversarial attacks: fast gradient sign method (FGSM), momentum iterative FGSM, and projected gradient descent method to analyze the susceptibility of the considered wireless application with and without adversarial training. We analyze the deep neural network (DNN) models performance against these attacks, where the adversarial perturbations are crafted using both the white-box and black-box attacks.

Healthcare, finance, defense, and the Internet of Things are all critical infrastructures that have become heavily dependent on artificial intelligence (AI), enabling them to analyze incoming data and make decisions within seconds, resulting in previously unprecedented efficiency and creativity. However, the application of AI in high-stakes scenarios also exposes the systems to malicious attacks, which exploit its data-driven learning processes. The review considers current research published between 2018 and 2025, indexed by Scopus, IEEE Xplore, Springer, and the ACM Digital Library, to systematically review the state of the art in adversarial attacks and defense mechanisms on AI systems. The report highlights the rising levels of sophistication and practical use of adversarial threats, particularly in autonomous vehicles, facial recognition, and medical diagnostics, by categorizing them into four key areas: evasion, poisoning, model inversion, and backdoor attacks. The outcomes of a critical assessment of defense strategies, such as adversarial training, robust optimization, input sanitization, anomaly detection, and ensembles, demonstrate that no single defense strategy can ensure total security. The discussion situates these findings within the broader context of cybersecurity, highlighting the challenges of scalability, the limitations of accepted assessment processes, and the ethical concerns surrounding accountability and compliance. Emerging technologies, such as blockchain, federated learning, and quantum-resistant defenses, hold promise in enhancing resilience. To secure AI systems and ensure their safe and trustworthy implementation into critical infrastructures, the study concludes that clarifying, adaptive, and transdisciplinary strategies are necessary.

We study two important concepts in adversarial deep learning---adversarial training and generative adversarial network (GAN). Adversarial training is the technique used to improve the robustness of discriminator by combining adversarial attacker and discriminator in the training phase. GAN is commonly used for image generation by jointly optimizing discriminator and generator. We show these two concepts are indeed closely related and can be used to strengthen each other---adding a generator to the adversarial training procedure can improve the robustness of discriminators, and adding an adversarial attack to GAN training can improve the convergence speed and lead to better generators. Combining these two insights, we develop a framework called Rob-GAN to jointly optimize generator and discriminator in the presence of adversarial attacks---the generator generates fake images to fool discriminator; the adversarial attacker perturbs real images to fool the discriminator, and the discriminator wants to minimize loss under fake and adversarial images. Through this end-to-end training procedure, we are able to simultaneously improve the convergence speed of GAN training, the quality of synthetic images, and the robustness of discriminator under strong adversarial attacks. Experimental results demonstrate that the obtained classifier is more robust than the state-of-the-art adversarial training approach, and the generator outperforms SN-GAN on ImageNet-143.