Jul 2026· Journal of Internet Technology· 0 citations
TL;DR
This survey research work proposes a lifecycle-based understanding of AI security threats and proposed a unified taxonomy for the four major categories of threats observed in real-world settings, namely, data poisoning and backdoor attacks on learning model updates, adversarial attacks on model outputs through input manipulation, privacy leakage through model-based queries, and model extraction for intellectual property theft and creation of rogue replicas of learning models.
Abstract
AI security is a key design criterion for IoT and edge cloud architectures where learning models are embedded near physical processes, receive streaming data from sensors, and are subject to continuous updates. This survey research work proposes a lifecycle-based understanding of AI security threats and proposed a unified taxonomy for the four major categories of threats observed in real-world settings, namely, data poisoning and backdoor attacks on learning model updates, adversarial attacks on model outputs through input manipulation, privacy leakage of confidential information through model-based queries, and model extraction for intellectual property theft and creation of rogue replicas of learning models. The research in surveying these defenses takes account of the limitations posed by the use of edge computing platforms from a computational standpoint, latency tolerance, network connections, and variety of hardware. These defense mechanisms include model provenance and data screening, robust training and backdoor attacks, monitoring and calibration, privacy-preserving learning and access control, and model protection through throttling, fingerprinting, watermarking, and attestation. Unlike prior surveys that treat these threats separately, this survey unifies them under a lifecycle-based taxonomy tailored to IoT and edge cloud deployments and emphasizes deployable defenses under latency, compute, and hardware constraints.
A lightweight edge AI framework that employs federated learning, enabling model training across distributed Internet of People and Things (IoP) devices without transferring raw data to centralised servers is proposed, enabling responsive, privacy-preserving, and resilient edge AI operations in distributed environments.
F. Philip-Kpae, A. Imoize, Lloyd Endurance Ogbondamati et al.· E3S Web of Conferences· 0 citations
A Federated Learning and LLM-Driven Threat Intelligence for Zero Trust IoT Architecture is presented, with FL for anomaly detection integrating privacy-preserving distributed learning, continuous identity verification, and LLM-driven autonomous threat response into a unified pipeline.
The rise of the Industrial IoT (IIoT) will result in a surge of IIoT devices with high-velocity data streams requiring rapid, real-time analysis of these data streams to power predictive maintenance and assure cybersecurity. Centralized cloud-based approaches to anomaly detection are hindered by their inherent latency and privacy issues while independent or stand-alone approaches to edge-based anomaly detection do not have enough data to effectively detect anomalies. This paper presents a federated learning framework to collaboratively develop an anomaly detection model from multiple edge nodes, without sharing the raw sensor data, so that data sovereignty is preserved. Two major contributions of this research include a lightweight hybrid secure aggregation method that utilizes pairwise additive masking and differential privacy, which mitigates the threat of inversion attacks achieved via a reconstruction SSIM < 0.05, and successfully detects >90% of model poisoning attempts, where as traditional homomorphic encryption solutions incur excessively high computational costs (approximately 68 ms/node) and 70 KB of communication overhead/round). Our architecture was validated using a synthetic IIoT data set containing 600,000 rows of data correlated across 12 edge nodes and 10 different types of sensors, and further validated using the real-world SWaT data set. The experimental results demonstrated the effectiveness of the framework, achieving an F1 score of 0.944 for anomaly detection, an F2 from centralized training of only 2.3%, and a 60-70% reduction in communication costs compared to the use of homomorphic encryption. The experimental results also demonstrate that local edge inference latency is <50 ms, meeting the real-time requirements of IIoT systems. Overall, the framework demonstrates that practical, deployable security for federated learning in IIoT is achievable without sacrificing accuracy or responsiveness, and open-source implementations are provided to ensure full reproducibility.
These findings demonstrate that Edge-ZTA provides an efficient, privacy-preserving, and scalable cybersecurity framework capable of mitigating sophisticated multi-stage cyberattacks while satisfying the stringent performance requirements of next-generation Industrial IoT infrastructures.
Ahmed Ramzi Rashid, Zaydon L. Ali, Ahmed Sedeeq Baker Al-Doori· Al-Noor Journal of Engineeri...· 0 citations
This review paper critically examines the integration of Artificial Intelligence (AI) and Machine Learning (ML) techniques to enhance information security within Cloud-IoT networks, focusing on hybrid Deep Learning models (CNN-LSTM), predictive analytics, and automated threat response mechanisms.
R. Saravanakumar, V.Anuratha, M.Elamparithi· International journal of com...· 0 citations
The Internet of Things (IoT) connects large numbers of devices that are often constrained, long-lived, and weakly secured, which makes IoT networks an attractive target for attackers. As artificial intelligence (AI) is increasingly used to manage these networks, the security picture changes in two ways at once. On one hand, machine learning and, more recently, agentic AI provide stronger tools for detecting and responding to threats. On the other hand, placing AI in control of the network introduces new risks of its own. In this review, the security and privacy of AI-managed IoT networks are examined from both directions. The main IoT threats are summarized, including botnets such as Mirai and the exploitation of known device vulnerabilities. The use of machine learning for intrusion detection is then reviewed, followed by the emerging use of large language model (LLM) based and agentic systems for autonomous defense and management. The new risks that arise when AI is given control, such as model manipulation, unreliable autonomous action, and an enlarged attack surface, are discussed, together with the privacy concerns raised by the large volumes of data these systems collect. Open challenges are identified, and directions for safer AI-managed IoT are suggested. A balanced view of both the promise and the hazards of managing IoT networks with AI is intended to be provided for practitioners and researchers.
Shiva Ram Rao, Vikram Malhotra· Advanced International Journ...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
