# Black-Box Ripper: Copying black-box models using generative evolutionary algorithms

Source: [Black-Box Ripper: Copying black-box models using generative evolutionary algorithms](<https://www.sota2.com/research/paper/68fa68891e209131cea1cc0d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:39:59.706Z

Authors: Antonio Barbalau, Adrian Cosma, Radu Tudor Ionescu, Marius Popescu

Published: 2020-10-21T17:25:23.000Z

## Abstract

We study the task of replicating the functionality of black-box neural models, for which we only know the output class probabilities provided for a set of input images. We assume back-propagation through the black-box model is not possible and its training images are not available, e.g. the model could be exposed only through an API. In this context, we present a teacher-student framework that can distill the black-box (teacher) model into a student model with minimal accuracy loss. To generate useful data samples for training the student, our framework (i) learns to generate images on a proxy data set (with images and classes different from those used to train the black-box) and (ii) applies an evolutionary strategy to make sure that each generated data sample exhibits a high response for a specific class when given as input to the black box. Our framework is compared with several baseline and state-of-the-art methods on three benchmark data sets. The empirical evidence indicates that our model is superior to the considered baselines. Although our method does not back-propagate through the black-box network, it generally surpasses state-of-the-art methods that regard the teacher as a glass-box model. Our code is available at: https://github.com/antoniobarbalau/black-box-ripper.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Model Stealing on CIFAR-10 (test)](<https://www.sota2.com/research/sota/model-stealing-on-cifar-10-test.md>): Model Stealing; CIFAR-10 (test); Synthetic Accuracy (Data-Free): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2010.11158>)

[PDF](<https://arxiv.org/pdf/2010.11158.pdf>)
