Enhancing network traffic detection via interpolation augmentation and contrastive learning
Lei Li, Qiang Zhou, Xinlong Yang, Linye Chen · 2025
Read Enhancing network traffic detection via interpolation augmentation and contrastive learning by Lei Li, Qiang Zhou, Xinlong Yang, Linye Chen (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12721505.txt.
Description
Lei Li and co-authors propose a better way to spot attacks in network traffic, in a 2025 paper. Older tools tend to read each flow of data on its own, so joint attacks spread across many flows can slip past. Real traffic data is also lopsided, with far more normal flows than attack flows.
Their method, called TICL, fills gaps in the data by blending samples to make new ones, which eases the lopsided mix. It also learns by contrast, pulling alike flows close and pushing unlike flows apart. Tests on two public data sets showed stronger detection than prior methods. The approach suits large networks where attack types keep changing.
Catalog record
| CREATOR | Lei Li, Qiang Zhou, Xinlong Yang, Linye Chen |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |