DeepAI AI Chat
Log In Sign Up

Smooth-Reduce: Leveraging Patches for Improved Certified Robustness

by   Ameya Joshi, et al.

Randomized smoothing (RS) has been shown to be a fast, scalable technique for certifying the robustness of deep neural network classifiers. However, methods based on RS require augmenting data with large amounts of noise, which leads to significant drops in accuracy. We propose a training-free, modified smoothing approach, Smooth-Reduce, that leverages patching and aggregation to provide improved classifier certificates. Our algorithm classifies overlapping patches extracted from an input image, and aggregates the predicted logits to certify a larger radius around the input. We study two aggregation schemes – max and mean – and show that both approaches provide better certificates in terms of certified accuracy, average certified radii and abstention rates as compared to concurrent approaches. We also provide theoretical guarantees for such certificates, and empirically show significant improvements over other randomized smoothing methods that require expensive retraining. Further, we extend our approach to videos and provide meaningful certificates for video classifiers. A project page can be found at


page 3

page 16


Improved, Deterministic Smoothing for L1 Certified Robustness

Randomized smoothing is a general technique for computing sample-depende...

Data Dependent Randomized Smoothing

Randomized smoothing is a recent technique that achieves state-of-art pe...

Robust and Accurate – Compositional Architectures for Randomized Smoothing

Randomized Smoothing (RS) is considered the state-of-the-art approach to...

Certifying Confidence via Randomized Smoothing

Randomized smoothing has been shown to provide good certified-robustness...

Boosting Randomized Smoothing with Variance Reduced Classifiers

Randomized Smoothing (RS) is a promising method for obtaining robustness...

Certified Defense via Latent Space Randomized Smoothing with Orthogonal Encoders

Randomized Smoothing (RS), being one of few provable defenses, has been ...

Scalable Certified Segmentation via Randomized Smoothing

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