---
title: "The Split Protocol Decides the Result: Re-Evaluating Encrypted Traffic Classification"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.06290v1"
permalink: "https://feed.astralor.com/items/itm_819bc0d170b3198bc94d2fd3"
published: "2026-11-04T10:25:50.000Z"
score: 61
channel: "tech"
tags: ["LLM","The Split Protocol","Decides","Result","Re-Evaluating Encrypted Traffic","Classification Encrypted","Encrypted","Nothing"]
---

# The Split Protocol Decides the Result: Re-Evaluating Encrypted Traffic Classification

## 速览

Encrypted traffic classifiers are routinely reported at 95-99% accuracy. We show that on one of two public corpora, the same model and code score macro-F1 0.992 under the evaluation protocol standard in the literature a…

## 关键点

- Encrypted traffic classifiers are routinely reported at 95-99% accuracy.
- We show that on one of two public corpora, the same model and code score macro-F1 0.992 under the evaluation protocol standard in the literature and 0.567 under a protocol that keeps flows from one packet capture on one…
- Nothing changes but the partition (gap 0.426 over eight seeds, p = 0.008 after Holm-Bonferroni correction).

## 全文

Encrypted traffic classifiers are routinely reported at 95-99% accuracy. We show that on one of two public corpora, the same model and code score macro-F1 0.992 under the evaluation protocol standard in the literature and 0.567 under a protocol that keeps flows from one packet capture on one side of the split. Nothing changes but the partition (gap 0.426 over eight seeds, p = 0.008 after Holm-Bonferroni correction). The inflation is not a property of random splitting as such. On a month of backbone QUIC traffic, we evaluate five split protocols at eight seeds each: random, temporal and client-disjoint splitting are statistically indistinguishable from session-disjoint, while server-disjoint splitting costs 0.192 macro-F1 (d = 17.0, p = 0.008). Which axis matters depends on how the corpus was collected, in a way invisible from its label space. We give a diagnostic that identifies the right axis before any model is trained: single-identifier probes. A decision tree on the capture identifier alone reaches 0.983 under a random split and exactly 0.000 under session-disjoint splitting. Under this evaluation, a metric-trained flow embedding leads four deep baselines but does not beat gradient-boosted trees on twenty packet sizes. Five of our own pre-registered architectural claims fail: distance-based rejection of unknown applications beats softmax thresholding, but ablating every metric objective makes rejection better, because class separation correlates at r = -0.88 with rejection quality. Few-shot enrollment is flat within a corpus but, across corpora, five labelled flows per class recover 91% of the deficit left by failed zero-shot transfer. All splits, results, code and negative findings are released.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_819bc0d170b3198bc94d2fd3