VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces
This addresses the challenge of scaling model extraction methods for complex, high-dimensional data, though it is incremental as it builds on existing techniques like SHAP and GANs.
The paper tackled the problem of black-box model extraction in high-dimensional spaces by using SHAP to enhance synthetic data generation, resulting in a 16.45% accuracy increase for image classification and up to 33.36% for video classification models.
In the domain of black-box model extraction, conventional methods reliant on soft labels or surrogate datasets struggle with scaling to high-dimensional input spaces and managing the complexity of an extensive array of interrelated classes. In this work, we present a novel approach that utilizes SHAP (SHapley Additive exPlanations) to enhance synthetic data generation. SHAP quantifies the individual contributions of each input feature towards the victim model's output, facilitating the optimization of an energy-based GAN towards a desirable output. This method significantly boosts performance, achieving a 16.45% increase in the accuracy of image classification models and extending to video classification models with an average improvement of 26.11% and a maximum of 33.36% on challenging datasets such as UCF11, UCF101, Kinetics 400, Kinetics 600, and Something-Something V2. We further demonstrate the effectiveness and practical utility of our method under various scenarios, including the availability of top-k prediction probabilities, top-k prediction labels, and top-1 labels.