Exploring Connections Between Active Learning and Model Extraction

TL;DR

This paper explores the relationship between active learning and model extraction attacks in machine learning, formalizing the attack process, discussing defenses, and leveraging active learning advancements to enhance attack strategies.

Contribution

It formalizes model extraction, draws parallels with active learning, and demonstrates how active learning techniques can improve attack effectiveness and inform defense strategies.

Findings

Active learning techniques can be adapted for effective model extraction attacks.

Understanding this connection helps in designing better defenses against model theft.

The paper provides a formal framework for analyzing model extraction vulnerabilities.

Abstract

Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model. However, such MLaaS systems raise privacy concerns such as model extraction. In model extraction attacks, adversaries maliciously exploit the query interface to steal the model. More precisely, in a model extraction attack, a good approximation of a sensitive or proprietary model held by the server is extracted (i.e. learned) by a dishonest user who interacts with the server only via the query interface. This attack was introduced by Tramer et al. at the 2016 USENIX Security Symposium, where practical attacks for various models were shown. We believe that better understanding the efficacy of model extraction attacks is paramount to designing secure MLaaS systems. To that end, we take the first step by (a) formalizing model extraction and discussing possible defense strategies, and (b) drawing parallels between model extraction and established area of active learning. In particular, we show that recent advancements in the active learning domain can be used to implement powerful model extraction attacks, and investigate possible defense strategies.