DeepAI AI Chat
Log In Sign Up

Localized Randomized Smoothing for Collective Robustness Certification

by   Jan Schuchardt, et al.

Models for image segmentation, node classification and many other tasks map a single input to multiple labels. By perturbing this single shared input (e.g. the image) an adversary can manipulate several predictions (e.g. misclassify several pixels). Collective robustness certification is the task of provably bounding the number of robust predictions under this threat model. The only dedicated method that goes beyond certifying each output independently is limited to strictly local models, where each prediction is associated with a small receptive field. We propose a more general collective robustness certificate for all types of models and further show that this approach is beneficial for the larger class of softly local models, where each output is dependent on the entire input but assigns different levels of importance to different input regions (e.g. based on their proximity in the image). The certificate is based on our novel localized randomized smoothing approach, where the random perturbation strength for different input regions is proportional to their importance for the outputs. Localized smoothing Pareto-dominates existing certificates on both image segmentation and node classification tasks, simultaneously offering higher accuracy and stronger guarantees.


Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks

In tasks like node classification, image segmentation, and named-entity ...

Center Smoothing for Certifiably Robust Vector-Valued Functions

Randomized smoothing has been successfully applied in high-dimensional i...

Scalable Certified Segmentation via Randomized Smoothing

We present a new certification method for image and point cloud segmenta...

SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions

State-of-the-art NLP models can often be fooled by human-unaware transfo...

Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

Top-k predictions are used in many real-world applications such as machi...

Invariance-Aware Randomized Smoothing Certificates

Building models that comply with the invariances inherent to different d...