MDV: Resolving the Auxiliary Data Dilemma in Model Extraction Defenses

Summary

Researchers present Model Defense Variational Autoencoder (MDV), a method against model extraction attacks (MEA), where attackers build a locally trained clone of a deep learning model. MDV replaces realistic auxiliary data, which is often absent, unstable in effect, and leaves some categories less protected, with virtual auxiliary data. The authors say experiments show it addresses these three problems.

Topics

• Adversarial machine learning

Related items

• InfoFingerprinting the Dispatchers behind Distributed Model ExtractionSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• 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)