Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2503.04174 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911035715223552 |
|---|---|
| author | Wu, Binghui Divakaran, Dinil Mon Gurusamy, Mohan |
| author_facet | Wu, Binghui Divakaran, Dinil Mon Gurusamy, Mohan |
| contents | As modern networks grow increasingly complex--driven by diverse devices, encrypted protocols, and evolving threats--network traffic analysis has become critically important. Existing machine learning models often rely only on a single representation of packets or flows, limiting their ability to capture the contextual relationships essential for robust analysis. Furthermore, task-specific architectures for supervised, semi-supervised, and unsupervised learning lead to inefficiencies in adapting to varying data formats and security tasks. To address these gaps, we propose UniNet, a unified framework that introduces a novel multi-granular traffic representation (T-Matrix), integrating session, flow, and packet-level features to provide comprehensive contextual information. Combined with T-Attent, a lightweight attention-based model, UniNet efficiently learns latent embeddings for diverse security tasks. Extensive evaluations across four key network security and privacy problems--anomaly detection, attack classification, IoT device identification, and encrypted website fingerprinting--demonstrate UniNet's significant performance gain over state-of-the-art methods, achieving higher accuracy, lower false positive rates, and improved scalability. By addressing the limitations of single-level models and unifying traffic analysis paradigms, UniNet sets a new benchmark for modern network security. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04174 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniNet: A Unified Multi-granular Traffic Modeling Framework for Network Security Wu, Binghui Divakaran, Dinil Mon Gurusamy, Mohan Cryptography and Security Machine Learning Networking and Internet Architecture As modern networks grow increasingly complex--driven by diverse devices, encrypted protocols, and evolving threats--network traffic analysis has become critically important. Existing machine learning models often rely only on a single representation of packets or flows, limiting their ability to capture the contextual relationships essential for robust analysis. Furthermore, task-specific architectures for supervised, semi-supervised, and unsupervised learning lead to inefficiencies in adapting to varying data formats and security tasks. To address these gaps, we propose UniNet, a unified framework that introduces a novel multi-granular traffic representation (T-Matrix), integrating session, flow, and packet-level features to provide comprehensive contextual information. Combined with T-Attent, a lightweight attention-based model, UniNet efficiently learns latent embeddings for diverse security tasks. Extensive evaluations across four key network security and privacy problems--anomaly detection, attack classification, IoT device identification, and encrypted website fingerprinting--demonstrate UniNet's significant performance gain over state-of-the-art methods, achieving higher accuracy, lower false positive rates, and improved scalability. By addressing the limitations of single-level models and unifying traffic analysis paradigms, UniNet sets a new benchmark for modern network security. |
| title | UniNet: A Unified Multi-granular Traffic Modeling Framework for Network Security |
| topic | Cryptography and Security Machine Learning Networking and Internet Architecture |
| url | https://arxiv.org/abs/2503.04174 |