The proliferation of Internet of Things (IoT) devices has introduced unprecedented security challenges, necessitating efficient intrusion detection systems (IDS) capable of operating under severe resource constraints. This research presents a hardware-informed empirical study of quantized neural-network-based intrusion detection for resource-constrained IoT platforms, using an ARM Cortex-M4 deployment target as a reference. We evaluate FP32, FP16, and INT8 TensorFlow Lite model variants derived from a lightweight 1D-CNN and assess their trade-offs in clean-data accuracy, model size, estimated inference latency, estimated energy consumption, and adversarial robustness. INT8-quantized model achieves 99.10% accuracy on clean data while maintaining 97.50% adversarial accuracy under Projected Gradient Descent (PGD) attacks with perturbation budget = 0.3. The quantized model achieves 12.0× latency reduction (0.083 vs. 0.995 ms) and 92.7% energy reduction (0.0083 vs. 0.1135 mJ) when compared to FP32. The memory footprint of the model is reduced by 55.7% from 58.02 to 25.72 KB. Our comprehensive analysis includes confusion matrices, ROC curves (AUC = 0.9964 for INT8), adversarial robustness heatmaps, and statistical significance testing via McNemar’s test. The results establish INT8 quantization as a viable solution for deploying robust IDS on resource-constrained IoT devices, achieving practical deployment feasibility without reducing detection performance.

Verification and Validation（V&V）are the most important and fundamental measures to ensure credibility of CFD software. Since the first version of the so-called WiseCFD platform published on 2004 to support CFD V&V, many efforts have been made to establish an open framework to support credibility assessment of CFD software as well. In this paper, the WiseCFD V2023 platform is presented, which is towards establishing an open framework to support V&V and credibility assessment of CFD software on Web. The new platform is developed based on the theory of credibility evaluation index system, and with technologies for standard V&V database, as well as technologies for standard interface of CFD data and software to breakthrough the key technologies such as open integration for different CFD software, open work flow definitions for different computation jobs, open definitions of V&V and credibility assessment tasks based on different choices of evaluation indexes, open V&V database behind the platform, and automatic verification and validation. The software platform is implemented with 3-level B/S software architecture, and is established through cloud native technologies such as microservices, containerization, and container orchestration for easy creation and deployment. The feasibility and efficiency of the presented platform is demonstrated through V&V and credibility assessment of typical CFD software for engineering applications.