Merge pull request #105 from sayakpaul/master

Adding mentions to Denoised Smoothing

Author: DualityGap

README.md

@@ -117,6 +117,7 @@ Structured Learning:
 *   [GAM: Graph Agreement Models for Semi-Supervised Learning](research/gam)
 *   [Neural Clustering Processes](research/neural_clustering)
 *   [CARLS: Cross-platform Asynchronous Representation Learning System](research/carls)
+*   [Denoised Smoothing: A Provable Defense for Pretrained Classifiers](research/third_party/denoised_smoothing)
 
 ## Featured Usage
 

research/README.md

@@ -44,3 +44,13 @@ certain TensorFlow versions or Python versions.
 
 [[4] A. Pakman, Y. Wang, C. Mitelut, J. Lee, L. Paninski. "Neural Clustering
 Processes." ICML 2020](https://arxiv.org/abs/1901.00409)
+
+## [Denoised Smoothing: A Provable Defense for Pretrained Classifiers](third_party/denoised_smoothing)
+
+The implementations of Denoised Smoothing [5] are provided in the
+`third_party/denoised_smoothing` folder on a strict "as is" basis, without warranties or
+conditions of any kind. Also, these implementations may not be compatible with
+certain TensorFlow versions or Python versions.
+
+[[5] H. Salman, M.Sun, C. Mitelut, G. Yang, A. Kapoor., Z. Kolter "Denoised Smoothing:
+A Provable Defense for Pretrained Classifiers." NeurIPS 2020](https://arxiv.org/abs/2003.01908)