Fingerprinting the Dispatchers behind Distributed Model Extraction

Summary

Researchers show that API distillation campaigns, which spread model-stealing requests across thousands of load-balanced accounts, can be linked through request timing even when content classifiers miss them. Using arrival and stream completion timestamps from a 20 percent seed set, the analysis ranks the remaining accounts of a campaign with 0.92 to 1.00 AUC within 20 minutes across thousands of production accounts. Pinning keys evades this detection but can severely throttle throughput when quotas bind.

Related items

• InfoModel Extraction of Convolutional Neural Networks with Max-PoolingSimilar attack · OpenAlex (peer-reviewed AI security)
• InfoTrustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and RobustnessSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoPreventing Model Extraction in Contextual Linear OptimizationSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoMapSteal: Map-based Autonomous Knowledge Stealing Attack Against Large Language ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoHow to Secure AI Models in Production Environments | Endor LabsSimilar attack · Endor Labs Blog