HiGAI-Net: Hierarchical Encrypted Traffic Classification for Generative AI Services
The Radio Access Network (RAN) today does not have a reliable way to identify GenAI traffic (ChatGPT, Microsoft Copilot, or Google Gemini traffic) at the bearer level. TLS~1.3 moves SNI into the encrypted handshake record, and Encrypted ClientHello (ECH) removes it entirely from passive inspection; Gemini has partly shifted to QUIC where SNI visibility also depends on whether ECH is deployed. Without per-flow application identity, differentiated QoS for GenAI services is not possible. HiGAI-Net tackles this using only packet-header metadata, stacking three independently trained classifiers: a binary AI/Non-AI gate (98.5 % weighted F1), a per-service resolver across ChatGPT, Copilot, and Gemini (86.4 %), and a text-vs-voice/video mode classifier (61.0 %). The core innovation is a suite of sliding-window temporal features that track how DL/UL byte-ratios evolve within a session -- the per-quarter and per-half ratio trends, a trend differential $ΔR$, and a streaming regularity index. Tested on 44,492 labeled flows, gradient-boosted tree models consistently outperformed all deep-learning variants; a per-flow label cache brings amortised inference below 1~$μ$s per packet.
Authors
- Madhan Raj Kanagarathinam (ORCID: https://orcid.org/0000-0002-1167-7389)
- Kapal Dev (ORCID: https://orcid.org/0000-0003-1262-8594)
- Jaheon Gu (ORCID: https://orcid.org/0000-0003-4214-8444)
- Krishna Moorthy Sivalingam (ORCID: https://orcid.org/0000-0001-8425-3432)
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.48550/arxiv.2611.22373
- Primary Topic
- Internet Traffic Analysis and Secure E-voting
- Type
- preprint