---
title: "Fingerprinting the Dispatchers behind Distributed Model Extraction"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.06661v1"
permalink: "https://feed.astralor.com/items/itm_e0d34e072c5026f9b0d59a1c"
published: "2026-11-04T15:36:56.000Z"
score: 55
channel: "tech"
tags: ["推理效率","Fingerprinting","Dispatchers","Distributed Model Extraction","API","However","Using"]
---

# Fingerprinting the Dispatchers behind Distributed Model Extraction

## At a glance

API distillation campaigns try to hide model-stealing traffic by splitting requests across thousands of load-balanced accounts, which standard content classifiers often miss. However, request timestamps, specifically ar…

## Key points

- API distillation campaigns try to hide model-stealing traffic by splitting requests across thousands of load-balanced accounts, which standard content classifiers often miss.
- However, request timestamps, specifically arrival time and stream completion time, reveal the underlying dispatching strategy, such as round-robin counters or key-shuffling pools.
- Using a 20 percent seed set, this timing analysis can forensically rank the remaining accounts of a campaign with 0.92 to 1.00 AUC within 20 minutes, even across thousands of real production accounts.

## Full text

API distillation campaigns try to hide model-stealing traffic by splitting requests across thousands of load-balanced accounts, which standard content classifiers often miss. However, request timestamps, specifically arrival time and stream completion time, reveal the underlying dispatching strategy, such as round-robin counters or key-shuffling pools. Using a 20 percent seed set, this timing analysis can forensically rank the remaining accounts of a campaign with 0.92 to 1.00 AUC within 20 minutes, even across thousands of real production accounts. While adaptive attackers struggle to hide rotating dispatchers using jitter, pinning keys successfully evades detection, though it can severely throttle throughput when quotas bind. Ultimately, timing exposes shared infrastructure patterns even when content filters fail.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_e0d34e072c5026f9b0d59a1c