Oct 2026· IEEE transactions on computers· Vol 75, pp. 3468-3482· 0 citations· 43 references
Abstract
Deep Neural Networks integrated into sensor-driven embedded systems have become fundamental to edge computing applications. While Inertial Measurement Units (IMUs) are ubiquitous in these architectures due to their cost-efficiency, the reliance on data-driven models expands the attack surface of the embedded computing pipeline. This paper investigates the vulnerability of such systems by presenting a synchronization-free backdoor attack framework. We address two critical threat models in the system lifecycle: training-data poisoning and outsourced training. For the poisoning setting, we exploit the physical-digital signal interface by developing a frequency-domain injection method that utilizes sidelobe perturbations to implant stealthy triggers. For the outsourced scenario, we propose a dual-optimization joint trigger learning scheme that co-optimizes trigger patterns and model objectives, eliminating the dependency on synchronization with the victim’s training process. To ensure attack stealthiness within the operational bounds, a dynamic weighting strategy is introduced to balance attack efficacy with benign inference accuracy. Extensive experiments on standard benchmarks demonstrate that current embedded architectures are highly susceptible to these methods: the frequency-domain poisoning achieves over 60% average attack success, while the outsourced-training attack exceeds 95%, highlighting a critical security gap in sensor-based intelligent systems.
Edge computing has emerged as a critical computing paradigm in modern distributed systems by migrating data processing closer to end users and Internet of Things (IoT) devices. While this paradigm decentralizes processes, minimizes latency, and reduces backhaul bandwidth congestion, it exponentially enlarges the cybera...
Zawad Yalmie Sazid, Robert Abbas· arXiv.org· 0 citations
A SOC-integrated, protocol-aware detection framework for 5G SA environments, combining structured telemetry ingestion, log normalization, decision-based detection logic, and analyst-oriented visualization within an Elastic-Stack-based SOC architecture is presented.
Miklós Orsós, A. Bánáti· Future Internet· 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 rapid proliferation of Internet of Things (IoT) systems has significantly increased the attack surface of modern cyber-physical infrastructures, creating the need for scalable, intelligent, and privacy-preserving security solutions. Traditional centralized intrusion detection approaches are limited by high communic...
Afef Slimani, K. Karoui· International Symposium on N...· 0 citations
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, and demonstrates that practical, deployable security for federated learning in IIoT is achievable without sacrificing accuracy or res...
This survey unifies a fragmented literature spanning perception pipelines, input-adaptive neural inference, input-adaptive neural inference, and autoregressive and agentic systems and provides a threat-model taxonomy, consolidated quantitative comparisons, a defense review by control mechanism, and open challenges such...
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.