Aug 2026· Journal of Cyber Security and Mobility· 0 citations
TL;DR
A constraint-aware adversarially robust Internet of Things (IoT) traffic classification system with protocol validity, device behavior consistency, and manifold-aware training and evaluation is presented, demonstrating improved robustness, realism, and deployability compared to existing approaches.
Abstract
A constraint-aware adversarially robust Internet of Things (IoT) traffic classification system with protocol validity, device behavior consistency, and manifold-aware training and evaluation is presented in this study. In realistic IoT communication semantics, resilience as a constrained min–max optimization problem allows adversarial perturbations. Comprehensive testing on sample IoT traffic datasets shows that baseline models achieve 95.1% accuracy under benign conditions but plummet following hostile attacks. The proposed defense reduces untargeted attack success rates to <18% while achieving 81.3% accuracy at ε=0.05 and 70.6% at ε=0.10. The proposed constraint-aware adversarial framework significantly enhances IoT traffic classification by achieving 97.4% accuracy and maintaining 90.6% robustness at ε=0.10, outperforming state-of-the-art methods. It reduces attack success rates to 11.2% (untargeted) and 7.9% (targeted) through protocol-compliant perturbations and manifold-aware learning. Additionally, the model achieves an efficient trade-off with 21.4 ms latency and 650 flows/sec throughput, making it suitable for real-time edge deployment. These results demonstrate improved robustness, realism, and deployability compared to existing approaches.
Federated Learning-Adaptive Gated Recurrent Unit is suggested, a Federated approach that combines a lightweight Gated Recurrent Unit (GRU) classifier with alternating adversarial fine-tuning on each client using FGSM and PGD, without any communication overhead, guaranteeing data-locality privacy through exchange of only model weights.
Deep learning has been widely deployed in critical scenarios such as the Internet of Things (IoT), industrial sensing, network intrusion detection, and cyber-physical system monitoring, where model inference directly affects system security, operational reliability, and service continuity. However, existing adversarial example detection studies remain insufficient for practical IoT deployment, as their validation often overlooks endpoint resource constraints, heterogeneous data modalities, physical environmental interference, communication protocol specifications, adaptive attacks, and adversary capability models. Moreover, detection outcomes are rarely connected with deployment locations, computational overhead, formal security assurance, and subsequent response strategies, which limits their engineering applicability. To address these limitations, this review systematically synthesizes recent representative studies in adversarial example detection and constructs a unified analytical framework integrating detection evidence, IoT deployment feasibility, and adaptive-attack evaluation. Based on the source of detection evidence, existing methods are categorized into input-consistency-based, feature-statistics-based, predictive-uncertainty-based, model-reconstruction-based, runtime-context-aware, and multi-strategy fusion detection, while formal certification is discussed as an independent security-assurance dimension. The review further analyzes the principles, applicable conditions, limitations, compatibility conflicts with IoT deployment constraints, and typical failure modes of these methods. The analysis identifies four key challenges: the lack of IoT-native adaptive evaluation, limited anomaly-boundary identification and cross-modal generalization, insufficient deployment-time security assurance, and weak coordination between detection decisions and security responses. Future research should therefore emphasize feasible attack paradigms, hierarchical lightweight detection, reliable multimodal fusion, certifiable operational boundaries, and auditable end-to-end response mechanisms, thereby supporting the evaluation and deployment of adversarial example detection in IoT scenarios.
Wenqiang Xu, Jian Li· Italian National Conference...· 0 citations
Modern Industrial Internet of Things (IIoT) integrates machine learning models for monitoring and control. However, they remain vulnerable to adversarial machine learning (AML) attacks, where an adversary adds small changes to the input data. These small changes degrade model quality, reduce accuracy, and can ultimately compromise the safety and security of the entire system. AML research in IIoT often focuses on individual attack types, defense methods, and datasets. Existing reviews lack a unified quantitative and system-level perspective. Therefore, a systematic literature review (SLR) is needed to provide a holistic analysis of existing attacks, defenses, and databases. This SLR analyzes 50 research articles to provide a holistic view of AML threats in IIoT systems and identifies seven distinct attack types: gradient-based perturbations, GAN-generated samples, poisoning attacks, reinforcement learning-based (RL) strategies, saliency-based feature manipulation, false data injection, and hybrid approaches. To illustrate the range of observed impacts, selected studies report the following degradation examples: saliency-based attacks cause accuracy reductions of 6–11 percentage points; iterative gradient attacks reduce accuracy from 95–99% to 30–40% in SIEM systems; and RL-based attacks reduce detection rates from 100% to 0% in rule-based IDS settings. In addition to the analysis of attack types, this SLR also evaluates current defense methods to protect IIoT systems. It has been observed that existing defense mechanisms lack generalization and require high computational resources. Moreover, the testing is performed under simplified threat models. The analysis of datasets further shows a clear gap between realistic industrial benchmarks (such as SWaT, WADI, and NSL-KDD) and synthetic datasets used for controlled experiments. By connecting attack behavior, defense performance, dataset characteristics, and system-level effects, this SLR identifies the key research gaps that must be addressed in future work.
Abeer Alsaidlani, Muhammad Rashid, M. Aljabri· Italian National Conference...· 0 citations
With the proliferation of Internet of Things (IoT), critical infrastructures such as smart cities, industrial automation, precision healthcare, and intelligent transportation have seen a significant shift in their security landscape. As these critical infrastructures are increasingly depending on OneM2M standards for interoperability and scalable service management, they are simultaneously presenting a larger and more structured attack surface. One of the most serious and realistic threats in such scenarios is black-box adversarial attacks, in which an attacker can compromise Machine Learning (ML) and Deep Learning (DL)-based intrusion detection systems (IDS) without having prior knowledge of the ML/DL model's architecture, parameters, and training data. To mitigate such a critical challenge, we propose a multi-stage framework specific to OneM2M-based IoT networks that can effectively counter transfer-based and query-based black-box adversarial attacks. Our framework's effectiveness will be tested on a dataset of 1.25 million labeled network flows collected from Azure IoT Hub-based IoT devices over a 10-day period. We will test the robustness of our framework against three adversarial attacks: FGSM with $\varepsilon=0.05$, PGD with 40 iterations and step size 0.01, and C&W with L2 optimization and 1,000 iterations. The proposed pipeline consists of four different mechanisms: (1) adversarial training with the use of mixed clean and adversarial samples, (2) traffic sanitization to minimize malicious and/or suspicious traffic flows before processing by the Common Service Entity (CSE), (3) the use of a black-box adversarial detector based on feature transformation, and (4) the use of an ensemble-based IDS to make use of the results of the Random Forest, XGBoost, MLP, and 1D-CNN-based IDSs via majority voting. The experimental results show that the proposed Ensemble + multi-defense configuration results in 98.1% accuracy, 98.3% TPR, and 1.7% FNR. Most notably, the proposed Ensemble + multi-defense configuration results in an ASR of 11.2%, which is down by 86% compared to the 82.3% ASR achieved by the baseline IDS. Notably, the proposed framework results in limited overheads in terms of RTT (increased by 8 ms), CPU (increased by 17%), and RAM (increased by 1.6 GB).
Hamza Jamiri, A. Zyane· International Conference on...· 0 citations
The integration of Software-Defined Networking (SDN) with large-scale Internet of Things (IoT) deployments enhances network programmability and visibility, yet it also introduces new security risks across emerging edge cloud computing environments. Deep Learning (DL) based autonomous anomaly detection (AAD) has emerged as a key defence mechanism for securing distributed and edge-enabled IoT infrastructures. Despite their effectiveness, the vulnerability of these DL models to adversarial attacks in SDN-IoT contexts remains underexplored, particularly in edge-cloud AI deployments, where models may operate across distributed infrastructures. This paper presents a comprehensive adversarial analysis of three representative DL architectures, CNN, LSTM, and AE-LSTM, evaluated across three diverse datasets: CICIDS2017, InSDN, and CICIoT2023. We investigate both data-level evasion attacks (FGSM, PGD) under white-box conditions and model-level threats via a noisebased Data Free Model Extraction (DFME) attack under realistic black-box conditions. Results reveal that minor perturbations can severely degrade detection performance, while DFME successfully reconstructs high-fidelity surrogate models without access to training data. These findings highlight significant integrity and confidentiality risks for AI-driven intrusion detection systems deployed across the edge-cloud continuum and emphasise the need for adversarially robust DL defences for distributed AAD systems in SDN-IoT networks.
Maxime Bossant, T. Yasarathna, Nhien-An Le-Khac· IEEE International Conferenc...· 0 citations
The rapid growth of Internet of Things (IoT) devices has significantly improved connectivity across smart environments. However, the resource-constrained nature of IoT devices and their limited built-in security mechanisms make them highly vulnerable to evolving cyberattacks. Traditional intrusion detection systems relying on signature-based or static rule sets are often ineffective against previously unseen attacks. This study proposes a hybrid machine learning-based intrusion detection and prevention framework for securing IoT networks. The framework integrates Isolation Forest, Autoencoder, Extreme Gradient Boosting, and Bidirectional Long Short-Term Memory models within a stacked ensemble architecture to improve attack detection while reducing false-positive predictions. The ensemble outputs are combined using a Logistic Regression meta-classifier to generate the final threat score. Experimental evaluation using the UNSW-NB15 dataset demonstrates that Extreme Gradient Boosting achieved the highest individual Receiver Operating Characteristic-Area Under the Curve score of 0.91, while the proposed framework further enhances detection robustness through ensemble learning and automated prevention. A Flask-based monitoring dashboard provides real-time visualization of detection results, blocked IP addresses, alerts, and system performance.
Ruthwik Palem, Likhith Reddy Peketi, Vanathi M et al.· Cureus Journal of Computer S...· 0 citations