资源受限环境下 IoT DDoS 检测迁移学习模型的可解释性评估
Explainability-Aware Evaluation of Transfer Learning Models for IoT DDoS Detection Under Resource Constraints
AI 导读
一项研究对七种预训练 CNN 架构在 CICDDoS2019 数据集上进行多类 IoT DDoS 检测的可解释性评估，结合性能指标、可靠性统计（MCC、Youden Index）、延迟与训练成本以及 Grad-CAM 和 SHAP 解释性分析。
正文 · 原文
Abstract:Distributed denial of service (DDoS) attacks threaten the availability of Internet of Things (IoT) infrastructures, particularly under resource-constrained deployment conditions. Although transfer learning models have shown promising detection accuracy, their reliability, computational feasibility, and interpretability in operational environments remain insufficiently explored. This study presents an explainability aware empirical evaluation of seven pre-trained convolutional neural network architectures for multi-class IoT DDoS detection using the CICDDoS2019 dataset and an image-based traffic representation. The analysis integrates performance metrics, reliability-oriented statistics (MCC, Youden Index, confidence intervals), latency and training cost assessment, and interpretability evaluation using Grad-CAM and SHAP. Results indicate that DenseNet and MobileNet based architectures achieve strong detection performance while demonstrating superior reliability and compact, class-consistent attribution patterns. DenseNet169 offers the strongest reliability and interpretability alignment, whereas MobileNetV3 provides an effective latency-accuracy trade-off for fog-level deployment. The findings emphasize the importance of combining performance, reliability, and explainability criteria when selecting deep learning models for IoT DDoS detection.
| Comments: | Updated version with several corrections, contains more clarification, and corrected typos in at the text and references |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.22488 [cs.CR] |
| (or arXiv:2602.22488v2 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2602.22488 arXiv-issued DOI via DataCite |
Submission history
From: Nelly Elsayed [view email]
[v1]
Wed, 25 Feb 2026 23:56:11 UTC (3,003 KB)
[v2]
Thu, 29 Oct 2026 03:31:36 UTC (2,670 KB)
来源：arXiv cs.AI · arxiv.org