Extracting Cloud-based Model with Prior Knowledge

TL;DR

This paper introduces an efficient model extraction attack leveraging prior knowledge from unlabeled datasets, significantly reducing query costs and improving attack fidelity on cloud-based models.

Contribution

It proposes a novel attack method that combines prior knowledge with posterior information, addressing overfitting and generalization issues in model extraction.

Findings

Achieves 95.1% fidelity with only 1.8K queries on real-world APIs

Reduces query cost to approximately $2.16 per attack

Generated adversarial examples have higher transferability

Abstract

Machine Learning-as-a-Service, a pay-as-you-go business pattern, is widely accepted by third-party users and developers. However, the open inference APIs may be utilized by malicious customers to conduct model extraction attacks, i.e., attackers can replicate a cloud-based black-box model merely via querying malicious examples. Existing model extraction attacks mainly depend on the posterior knowledge (i.e., predictions of query samples) from Oracle. Thus, they either require high query overhead to simulate the decision boundary, or suffer from generalization errors and overfitting problems due to query budget limitations. To mitigate it, this work proposes an efficient model extraction attack based on prior knowledge for the first time. The insight is that prior knowledge of unlabeled proxy datasets is conducive to the search for the decision boundary (e.g., informative samples). Specifically, we leverage self-supervised learning including autoencoder and contrastive learning to pre-compile the prior knowledge of the proxy dataset into the feature extractor of the substitute model. Then we adopt entropy to measure and sample the most informative examples to query the target model. Our design leverages both prior and posterior knowledge to extract the model and thus eliminates generalizability errors and overfitting problems. We conduct extensive experiments on open APIs like Traffic Recognition, Flower Recognition, Moderation Recognition, and NSFW Recognition from real-world platforms, Azure and Clarifai. The experimental results demonstrate the effectiveness and efficiency of our attack. For example, our attack achieves 95.1% fidelity with merely 1.8K queries (cost 2.16$) on the NSFW Recognition API. Also, the adversarial examples generated with our substitute model have better transferability than others, which reveals that our scheme is more conducive to downstream attacks.