arXiv:2510. 13817v2 Announce Type: replace Abstract: The growth of IoT devices in shared environments has outpaced our ability to identify them, posing urgent risks to privacy, safety, and accountability.
The paper investigates whether machine learning models for IoT intrusion detection truly learn attack patterns or rely on dataset shortcuts. Using the CyberFlowIoT-GICAP benchmark, the authors evaluate four learning paradigms across different feature sets and split strategies, finding that performance is largely driven by feature representation and that tree-based models can exploit temporal artifacts. The study also highlights asymmetric attack detectability and proposes a four-point protocol checklist for realistic evaluation.
The paper investigates whether passive motion traces recorded during selfie capture can serve as an auxiliary signal for detecting spoofing and verifying users in mobile remote identity verification systems. It introduces the CanSelfie dataset, comprising 375 multi‑sensor sequences from 30 participants, and evaluates seven time‑series classifiers and eight anomaly detectors across various sensor configurations. Results show that accelerometer‑only classifiers achieve very low false rejection rates, while certain models achieve low false acceptance rates and high verification accuracy, indicating that selfie‑capture motion is a promising low‑friction evidence channel.
arXiv:2609.09257v1 Announce Type: cross Abstract: Sensor-based AI systems are rarely operated under the conditions under which they were trained: devices, personnel and recording epochs change, and e...
arXiv:2608. 15761v1 Announce Type: cross Abstract: Edge-IIoTset is the reference benchmark for machine-learning intrusion detection in the industrial Internet of Things, and results reported on it cluster above 99%.
The study investigates the vulnerability of a hybrid variational quantum classifier (VQC) used for network intrusion detection to adversarial attacks. By training on the Friday DDoS subset of CICIDS2017, the authors evaluate label‑flipping during training and FGSM evasion at prediction time, comparing results in simulation and on IBM’s Fez superconducting processor (Heron r2). They find that models with similar accuracy can differ markedly in attack resilience: a low‑confidence model loses half its detections to minor input changes, whereas a high‑confidence model requires larger perturbations to fail. Importantly, attacks crafted in simulation transfer to real hardware, and simulated device noise reduces confidence—making attacks easier—without lowering accuracy, indicating that accuracy alone does not reveal a model’s exposure.
arXiv:2610.27135v1 Announce Type: cross Abstract: With the advancement of powerful AI chips, on-device machine learning is gaining traction for its low latency and privacy protection. However, when e...
arXiv:2610.27152v1 Announce Type: cross Abstract: Neural networks (NNs) are increasingly deployed on edge devices such as mobile and IoT platforms, offering low latency and improved privacy compared...
arXiv:2610.02552v1 Announce Type: cross Abstract: Machine learning-based intrusion detection systems (IDS) are critical for securing Industrial Internet of Things (IIoT) environments. Most adversaria...
arXiv:2606. 02256v1 Announce Type: new Abstract: Our work presents a method for ECG segmentation and arrhythmia detection using Tiny Machine Learning (TinyML) models for real-time, on-device inference on resource-constrained embedded systems.
TERMon is a lightweight hardware runtime monitor designed for edge AI accelerators in safety‑critical environments. It detects persistent behavioral threats—such as model corruption, distribution shift, and adversarial inputs—by observing inference behavior through hardware‑efficient ternary patterns matched against a thermometer‑encoded fingerprint. Implemented on a PYNQ‑Z2 FPGA, TERMon operates with a two‑cycle decision latency and requires no on‑chip block RAM or DSPs.
arXiv:2606. 14987v1 Announce Type: cross Abstract: Internet of Things (IoT) and Cyber-physical systems (CPS) increasingly rely on continual learning (CL) to adapt to evolving environments, device heterogeneity, and concept drift, thereby improving overall utility.