DomainDynamics: Advancing lifecycle-based risk assessment of domain names
Daiki Chiba, Hiroki Nakano, Takashi Koide · Computers & Security · 2025
The persistent threat of malicious domains in cybersecurity necessitates robust detection systems. Traditional machine learning approaches often struggle to accurately assess domain name risks due to their static analysis methods and lack of consideration for temporal changes in domain attributes. To address these limitations, we developed DomainDynamics, a novel system that evaluates domain name risks by analyzing their lifecycle phases. This study provides a comprehensive evaluation and refinement of the DomainDynamics framework. The system creates temporal profiles for domains and assesses their attributes at various stages, enabling informed, time-sensitive risk assessments. Our initial evaluation, involving over 85,000 malicious domains, achieved an 82.58% detection rate with a low 0.41% false positive rate. We expanded our research to include benchmarking against commercial services, feature significance analysis using interpretable AI techniques, and detailed case studies. This investigation not only validates the effectiveness of DomainDynamics but also reveals temporal indicators of malicious intent. Our findings demonstrate the advantages of lifecycle-based analysis over static methodologies, providing valuable insights for practical cybersecurity applications. • DomainDynamics: lifecycle-based detection (82.58% Detection Rate, 0.41% FPR). • Temporal analysis outperforms static methods on 85,000+ malicious domains. • Explainable AI offers deep insights into domain risk through real case studies. • Benchmarks against commercial tools confirm lifecycle indicators’ significance. • Enhances malicious domain detection via temporal context and dynamic changes.