← 研踪 PaperTrailarXiv:2611.22373 · v1
HiGAI-Net: Hierarchical Encrypted Traffic Classification for Generative AI Services
首次提交 2026-11-17 16:26
版本更新 2026-11-17 16:26
雷达观测 2026-11-18 19:42
摘要
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 , 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~s per packet.
作者备注:Paper accepted in IEEE Globecom 2026
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 16:26 · 最新观测版本
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 , 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~s per packet.
查看此版本解读 →查看此版本原文 ↗