arxiv6.0 / 10

Fingerprinting the Dispatchers behind Distributed Model Extraction

Snigdha Chandan Khilar

Abstract

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.

Research area

ai securitymodel evaluationsrobustness
Published
4 Nov 2026
Source
arxiv
View paper
Sign in to read and join the discussion.