Model Extraction Warning in MLaaS Paradigm
This addresses security concerns for cloud vendors and model owners in MLaaS by providing a warning system against extraction attacks, though it is incremental as it builds on existing extraction attack research.
The paper tackles the problem of model extraction attacks in Machine Learning as a Service (MLaaS) by proposing a cloud-based monitor that quantifies extraction status using information gain and intelligent query summaries, achieving low computational overhead and demonstrating performance on decision tree models with open source datasets.
Cloud vendors are increasingly offering machine learning services as part of their platform and services portfolios. These services enable the deployment of machine learning models on the cloud that are offered on a pay-per-query basis to application developers and end users. However recent work has shown that the hosted models are susceptible to extraction attacks. Adversaries may launch queries to steal the model and compromise future query payments or privacy of the training data. In this work, we present a cloud-based extraction monitor that can quantify the extraction status of models by observing the query and response streams of both individual and colluding adversarial users. We present a novel technique that uses information gain to measure the model learning rate by users with increasing number of queries. Additionally, we present an alternate technique that maintains intelligent query summaries to measure the learning rate relative to the coverage of the input feature space in the presence of collusion. Both these approaches have low computational overhead and can easily be offered as services to model owners to warn them of possible extraction attacks from adversaries. We present performance results for these approaches for decision tree models deployed on BigML MLaaS platform, using open source datasets and different adversarial attack strategies.