Timezone: »

Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
Antonio Barbalau · Adrian Cosma · Radu Tudor Ionescu · Marius Popescu

Thu Dec 10 06:00 AM -- 06:15 AM (PST) @ Orals & Spotlights: Optimization/Theory

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.

Author Information

Antonio Barbalau (University of Bucharest)
Adrian Cosma (Politehnica University of Bucharest)
Radu Tudor Ionescu (University of Bucharest)
Marius Popescu (University of Bucharest)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors