Architectural Selection Framework for Synthetic Network Traffic: Quantifying the Fidelity-Utility Trade-off

Computer Science > Cryptography and Security [Submitted on 18 Oct 2024 (v1), last revised 13 Mar 2026 (this version, v3)] Architectural Selection Framework for Synthetic Network Traffic: Quantifying the Fidelity-Utility Trade-off Dure Adan Ammara, Jianguo Ding, Kurt Tutschku The fidelity and utility of synthetic network traffic are critically compromised by architectural mismatch across heterogeneous network datasets and prevalent scalability failure. This study addresses this challenge by establishing an Architectural Selection Framework that empirically quantifies how data structure compatibility dictates the optimal fidelity-utility trade-off. We systematically evaluate twelve generative architectures (both non-AI and AI) across two distinct data structure types: categorical-heavy NSL-KDD and continuous-flow-heavy CIC-IDS2017. Fidelity is rigorously assessed through three structural metrics (Data Structure, Correlation, and Probability Distribution Difference) to confirm structural realism before evaluating downstream utility. Our results, confirmed over twenty independent runs (N=20), demonstrate that GAN-based models (CTGAN, CopulaGAN) exhibit superior architectural robustness, consistently achieving the optimal balance of statistical fidelity and practical utility. Conversely, the framework exposes critical failure modes, i.e., statistical methods compromise structural fidelity for utility (Compromised fidelity), and modern iterative architectures, such as Diffusion Models, face prohibitive computational barriers, rendering them impractical for large-scale security deployment. This contribution provides security practitioners with an evidence-based guide for mitigating architectural failures, thereby setting a benchmark for reliable and scalable synthetic data deployment in adaptive security solutions. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2410.16326 [cs.CR]   (or arXiv:2410.16326v3 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2410.16326 Focus to learn more Journal reference: IEEE Access, vol 14, pp 468-484, 2026 Related DOI: https://doi.org/10.1109/ACCESS.2025.3646769 Focus to learn more Submission history From: Dure Adan Ammara [view email] [v1] Fri, 18 Oct 2024 14:19:25 UTC (1,078 KB) [v2] Sat, 22 Feb 2025 07:50:31 UTC (22,011 KB) [v3] Fri, 13 Mar 2026 12:07:03 UTC (7,299 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2024-10 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)