Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data

Abstract

We study design of black-box model extraction attacks that can send minimal number of queries from a publicly available dataset to a target ML model through a predictive API with an aim to create an informative and distributionally equivalent replica of the target. First, we define distributionally equivalent and Max-Information model extraction attacks, and reduce them into a variational optimisation problem. The attacker sequentially solves this optimisation problem to select the most informative queries that simultaneously maximise the entropy and reduce the mismatch between the target and the stolen models. This leads to an active sampling-based query selection algorithm, Marich, which is model-oblivious. Then, we evaluate Marich on different text and image data sets, and different models, including CNNs and BERT. Marich extracts models that achieve $\sim 60-95\%$ of true model's accuracy and uses $\sim 1,000-8,500$ queries from the publicly available datasets, which are different from the private training datasets. Models extracted by Marich yield prediction distributions, which are $\sim 2-4\times$ closer to the target's distribution in comparison to the existing active sampling-based attacks. The extracted models also lead to $84-96\%$ accuracy under membership inference attacks. Experimental results validate that Marich is query-efficient, and capable of performing task-accurate, high-fidelity, and informative model extraction.

arXiv commentPresented in the Privacy-Preserving AI (PPAI) workshop at AAAI 2023 as a spotlight talk and published in NeurIPS 2023

References in corpus (11)

• Deep Learning with Differential Privacy
• Character-level Convolutional Networks for Text Classification
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• Differentially Private Empirical Risk Minimization
• Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data
• RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning
• MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI
• Stateful Detection of Model Extraction Attacks
• DeepAL: Deep Active Learning in Python
• Minimum-Margin Active Learning