CIC-YNU-IoTMal: Multilayer Dataset for Static & Dynamic Analysis of IoT Malware Behaviour

Item: CIC-YNU-IoTMal: Multilayer Dataset for Static & Dynamic Analysis of IoT Malware Behaviour
Rating: 4
Author: PostSingularity Institute

by Ogobuchi Daniel

Applied Sciences & Engineering Computing & Cybersecurity URComputer security URJComputer viruses, Trojans and worms

🎙 Ogobuchi Daniel 👥 1K 📅 May 4, 2026 ⏱ 38 min 👁 250 📄 expert opinion 🧭 2026-08-15

Available in: English (current) Français

Keywords

IoT malwaredatasetstatic analysisdynamic analysiscross-architecture

Summary

The webinar presents the CIC-YNU-IoTMal 2026 dataset, a multilayer dataset for IoT malware analysis. The speaker, Ogobuchi Daniel, a PhD candidate, introduces the dataset developed in collaboration between the Canadian Institute for Cybersecurity (CIC), Yokohama National University, and NICT Japan. The dataset addresses the scarcity of comprehensive IoT malware datasets by combining static and dynamic analysis across four CPU architectures: ARM, MIPS, MIPSEL, and x86. It includes network traffic, system traces, and system activity reports collected from executing malware samples in a controlled sandbox environment. The dataset covers eight malware families and includes a novel approach for generating benign samples using AI. The presentation outlines the dataset’s generation protocol, feature extraction, and validation using multiple machine learning algorithms. The dataset is publicly available, and the speaker highlights its potential for cross-architecture generalization and zero-day detection research. The talk concludes with a Q&A session where the speaker advises on dataset selection for research.

152 words

Critical Evaluation

Value of the Information & Strength of the Argument

The presentation provides valuable information about a new dataset that addresses a gap in IoT malware research. The speaker clearly explains the motivation, methodology, and potential applications of the dataset. The argumentation is solid, supported by statistics on IoT device growth and malware attack trends. However, the talk is more of an overview than a deep technical dive, and the speaker does not provide detailed evidence of the dataset’s effectiveness beyond mentioning validation results. The value lies in the dataset’s public availability and its design for cross-architecture analysis, which is a significant contribution to the field.

Scientific Rigor, Source Quality, Title Accuracy

The presentation demonstrates scientific rigor through a structured methodology and references to a published paper. The speaker mentions the collaboration with reputable institutions and the dataset’s availability. However, the talk does not cite specific sources during the presentation, and the description provides links to the institute’s website and social media, but not directly to the dataset or paper. The title accurately reflects the content, focusing on the dataset’s static and dynamic analysis aspects. The speaker’s expertise and the institutional backing enhance the credibility, but the lack of direct source citations in the talk limits the ability to verify claims independently.

211 words

Title / Content Match

The title accurately reflects the content, which focuses on the introduction and features of the CIC-YNU-IoTMal dataset.

Quality & Reliability

8/10

The presentation is given by a PhD candidate with relevant expertise, and the dataset is described in detail with a clear methodology. The talk is part of a reputable institute's webinar series. However, the presentation is a summary of a published paper, and the speaker does not provide in-depth technical details or independent verification of the claims.

Key Moments

Markers derived by PSI from the transcript: the creator did not define chapters.

Cited Sources

CIC Website — Mentioned as the hosting institution and for more information about the Canadian Institute for Cybersecurity.
CIC Blog — Provided in the description as a resource for cybersecurity news and updates.
CIC LinkedIn — Provided in the description for professional networking and updates.
CIC Facebook — Provided in the description for social media updates.
CIC YouTube Channel — Referenced in the description as a video about the Canadian Institute for Cybersecurity.

Concurring Sources

CIC Website — The institute's website provides information about their research and datasets, supporting the credibility of the presentation.

Contribution & Novelties

The CIC-YNU-IoTMal dataset provides a novel contribution by combining static and dynamic analysis across multiple IoT architectures, addressing the scarcity of comprehensive datasets. The inclusion of a benign sample generation method using AI is innovative. The dataset’s public availability and detailed documentation enable reproducibility and further research.

Pour aller plus loin :

IoT malware analysis — Overview of IoT malware and its challenges.
Static and dynamic analysis — Explanation of malware analysis techniques.
Cross-architecture analysis — General concept of cross-platform compatibility, relevant to the dataset’s design.

86 words

Radar Profile

The radar profile shows high scores in quality and reliability, with moderate scores in quantity and technical level. This indicates a well-structured and credible presentation, though it may not delve deeply into technical details, making it suitable for a broad audience.

Reliability 8/10

💬 No comments were provided for analysis.