Certifying Model Accuracy under Distribution Shifts
Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution. In this work, we present provable robustness guarantees on the accuracy of a model under bounded Wasserstein shifts of the data distribution. We show that a simple procedure that randomizes the input of the model within a transformation space is provably robust to distributional shifts under the transformation. Our framework allows the datum-specific perturbation size to vary across different points in the input distribution and is general enough to include fixed-sized perturbations as well. Our certificates produce guaranteed lower bounds on the performance of the model for any (natural or adversarial) shift of the input distribution within a Wasserstein ball around the original distribution. We apply our technique to: (i) certify robustness against natural (non-adversarial) transformations of images such as color shifts, hue shifts and changes in brightness and saturation, (ii) certify robustness against adversarial shifts of the input distribution, and (iii) show provable lower bounds (hardness results) on the performance of models trained on so-called "unlearnable" datasets that have been poisoned to interfere with model training.
Code (1)
Tasks
modelSimilar Papers 제목 키워드 기반
Semantic Robustness Certification for Vision-Language Models
Vision-language models (VLMs) are now widely used in downstream tasks. However, real-world applications often expose VLMs to distribution shifts induced by semantic variation (e.g., shape, size, and style). Robustness ce…
Certifying Out-of-Domain Generalization for Blackbox Functions
Certifying the robustness of model performance under bounded data distribution drifts has recently attracted intensive interest under the umbrella of distributional robustness. However, existing techniques either make st…
Domain GeneralizationToward Certified Robustness Against Real-World Distribution Shifts
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts. To do so, we bridge the gap between hand-crafted specifications and realistic deployment settings by pr…
Distributionally Robust PAC-Bayesian Control
We present a distributionally robust PAC-Bayesian framework for certifying the performance of learning-based finite-horizon controllers. While existing PAC-Bayes control literature typically assumes bounded losses and ma…
Transferring Fairness under Distribution Shifts via Fair Consistency Regularization
The increasing reliance on ML models in high-stakes tasks has raised a major concern on fairness violations. Although there has been a surge of work that improves algorithmic fairness, most of them are under the assumpti…
Fairness