Minimal implementation of Denoised Smoothing: A Provable Defense for Pretrained Classifiers in TensorFlow.

Overview

Denoised-Smoothing-TF

Minimal implementation of Denoised Smoothing: A Provable Defense for Pretrained Classifiers in TensorFlow.

Denoised Smoothing is a simple and elegant way to (provably) robustify pre-trained image classification models (including the cloud APIs with only query access) and l2 adversarial attacks. This blog post provides a nice introduction to the method. The figure below summarizes what Denoised Smoothing is and how it works:


  • Take a pre-trained classifier and prepend a pre-trained denoiser with it. Of course, the dataset on which the classifier and the denoiser would need to be trained on the same/similar dataset.
  • Apply Randomized Smoothing.

Randomized Smoothing is a well-tested method to provably defend against l2 adversarial attacks under a specific radii. But it assumes that a classifier performs well under Gaussian noisy perturbations which may not always be the case.

Note: I utilized many scripts from the official repository of Denoised Smoothing to develop this repository. My aim with this repository is to provide a template for researchers to conduct certification tests with Keras/TensorFlow models. I encourage the readers to check out the original repository, it's really well-developed.

Further notes

All the notebooks can be executed on Colab! You also have the option to train using the free TPUs.

Results

Denoiser with stability objective Denoiser with MSE objective

As we can see prepending a pre-trained denoiser is extremely helpful for our purpose.

Models

The models are available inside models.tar.gz in the SavedModel format. In the interest of reproducibility, the initial model weights are also provided.

Acknowledgements

Paper citation

@inproceedings{NEURIPS2020_f9fd2624,
 author = {Salman, Hadi and Sun, Mingjie and Yang, Greg and Kapoor, Ashish and Kolter, J. Zico},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},
 pages = {21945--21957},
 publisher = {Curran Associates, Inc.},
 title = {Denoised Smoothing: A Provable Defense for Pretrained Classifiers},
 url = {https://proceedings.neurips.cc/paper/2020/file/f9fd2624beefbc7808e4e405d73f57ab-Paper.pdf},
 volume = {33},
 year = {2020}
}
Owner
Sayak Paul
Trying to learn how machines learn.
Sayak Paul
Fedlearn支持前沿算法研发的Python工具库 | Fedlearn algorithm toolkit for researchers

FedLearn-algo Installation Development Environment Checklist python3 (3.6 or 3.7) is required. To configure and check the development environment is c

89 Nov 14, 2022
Dyalog-apl-docset - Dyalog APL Dash Docset Generator

Dyalog APL Dash Docset Generator o alasa e kili sona kepeken tenpo lili a A Dash

Maciej Goszczycki 1 Jan 10, 2022
Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning Source Code

Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning Trevor Ablett*, Bryan Chan*,

STARS Laboratory 8 Sep 14, 2022
Swapping face using Face Mesh with TensorFlow Lite

Swapping face using Face Mesh with TensorFlow Lite

iwatake 17 Apr 26, 2022
[NeurIPS 2021] Well-tuned Simple Nets Excel on Tabular Datasets

[NeurIPS 2021] Well-tuned Simple Nets Excel on Tabular Datasets Introduction This repo contains the source code accompanying the paper: Well-tuned Sim

52 Jan 04, 2023
Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

MASTER-PyTorch PyTorch reimplementation of "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021). This projec

Wenwen Yu 255 Dec 29, 2022
Model of an AI powered sign language interpreter.

TEXT AND SPEECH TO SIGN LANGUAGE. A web application which takes in text or live audio speech recording as input, converts and displays the relevant Si

Mark Gatere 4 Mar 30, 2022
Captcha-tensorflow - Image Captcha Solving Using TensorFlow and CNN Model. Accuracy 90%+

Captcha Solving Using TensorFlow Introduction Solve captcha using TensorFlow. Learn CNN and TensorFlow by a practical project. Follow the steps, run t

Jackon Yang 869 Jan 06, 2023
MM1 and MMC Queue Simulation using python - Results and parameters in excel and csv files

implementation of MM1 and MMC Queue on randomly generated data and evaluate simulation results then compare with analytical results and draw a plot curve for them, simulate some integrals and compare

Mohamadreza Rezaei 1 Jan 19, 2022
Attention-guided gan for synthesizing IR images

SI-AGAN Attention-guided gan for synthesizing IR images This repository contains the Tensorflow code for "Pedestrian Gender Recognition by Style Trans

1 Oct 25, 2021
TensorFlow implementation of Elastic Weight Consolidation

Elastic weight consolidation Introduction A TensorFlow implementation of elastic weight consolidation as presented in Overcoming catastrophic forgetti

James Stokes 67 Oct 11, 2022
[CVPRW 21] "BNN - BN = ? Training Binary Neural Networks without Batch Normalization", Tianlong Chen, Zhenyu Zhang, Xu Ouyang, Zechun Liu, Zhiqiang Shen, Zhangyang Wang

BNN - BN = ? Training Binary Neural Networks without Batch Normalization Codes for this paper BNN - BN = ? Training Binary Neural Networks without Bat

VITA 40 Dec 30, 2022
PyTorch implementation of the paper Deep Networks from the Principle of Rate Reduction

Deep Networks from the Principle of Rate Reduction This repository is the official PyTorch implementation of the paper Deep Networks from the Principl

459 Dec 27, 2022
PyTorch implementations of neural network models for keyword spotting

Honk: CNNs for Keyword Spotting Honk is a PyTorch reimplementation of Google's TensorFlow convolutional neural networks for keyword spotting, which ac

Castorini 475 Dec 15, 2022
PyTorch Code for NeurIPS 2021 paper Anti-Backdoor Learning: Training Clean Models on Poisoned Data.

Anti-Backdoor Learning PyTorch Code for NeurIPS 2021 paper Anti-Backdoor Learning: Training Clean Models on Poisoned Data. Check the unlearning effect

Yige-Li 51 Dec 07, 2022
Lip Reading - Cross Audio-Visual Recognition using 3D Convolutional Neural Networks

Lip Reading - Cross Audio-Visual Recognition using 3D Convolutional Neural Networks - Official Project Page This repository contains the code develope

Amirsina Torfi 1.7k Dec 18, 2022
The materials used in the SaxonJS tutorial presented at Declarative Amsterdam, 2021

SaxonJS-Tutorial-2021, version 1.0.4 Last updated on 4 November, 2021. Table of contents Background Prerequisites Starting a web server Running a Java

Saxonica 11 Oct 23, 2022
[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver

Shape As Points (SAP) Paper | Project Page | Short Video (6 min) | Long Video (12 min) This repository contains the implementation of the paper: Shape

394 Dec 30, 2022
DCA - Official Python implementation of Delaunay Component Analysis algorithm

Delaunay Component Analysis (DCA) Official Python implementation of the Delaunay

Petra Poklukar 9 Sep 06, 2022
Texture mapping with variational auto-encoders

vae-textures This is an experiment with using variational autoencoders (VAEs) to perform mesh parameterization. This was also my first project using J

Alex Nichol 41 May 24, 2022