Synthetic images from diffusion model APIs can train substitute models that extract black-box classifiers and enable high-success adversarial transfer attacks with 0.01x the query budget of prior methods.
VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Explore the vulnerability of black-box models via diffusion models
Synthetic images from diffusion model APIs can train substitute models that extract black-box classifiers and enable high-success adversarial transfer attacks with 0.01x the query budget of prior methods.