Anonymize BLM Protest Images

Overview

Anonymize BLM Protest Images

This repository automates @BLMPrivacyBot, a Twitter bot that shows the anonymized images to help keep protesters safe. Use our interface at blm.stanford.edu.

What's happened? Arrests at protests from public images

Over the past weeks, we have seen an increasing number of arrests at BLM protests, with images circulating around the web enabling automatic identification of those individuals and subsequent arrests to hamper protest activity. This primarily concerns social media protest images.

Numerous applications have emerged in response to this threat that aim to anonymize protest images and enable people to continue protesting in safety. Of course, this would require a shift on the public's part to recognize this issue and an easy and effective method for anonymization to surface. In an ideal world, platforms like Twitter would enable an on-platform solution.

So what's your goal? AI to help alleviate some of the worst parts of AI

The goal of this work is to leverage our group's knowledge of facial recognition AI to offer the most effective anonymization tool that evades the state of the art in facial recognition technology. AI facial recognition models can still recognize blurred faces. This work tries to discourage people from trying to recognize or reconstruct pixelated faces by masking people with an opaque mask. We use the BLM fist emoji as that mask for solidarity. While posting anonymized images does not delete the originals, we are starting with awareness and hope Twitter and other platforms would offer an on-platform solution (might be a tall order, but one can hope).

Importantly, this application does not save images. We hope the transparency of this repository will allow for community input. The Twitter bot posts anonymized images based on the Fair Use policy; however, if your image is used and you'd like it to be taken down, we will do our best to do so immediately.

Q&A

How can AI models still recognize blurred faces, even if they cannot reconstruct them perfectly? Recognition is different from reconstruction. Facial recognition technology can still identify many blurred faces and is better than humans at it. Reconstruction is a much more arduous task (see the difference between discriminative and generative models, if you're curious). Reconstruction has recently been exposed to be very biased (see lessons from PULSE). Blurring faces has the added threat of encouraging certain people or groups to de-anonymize images through reconstruction or directly identifying individuals through recognition.

Do you save my pre-anonymized images? No. The goal of this tool is to protect your privacy and saving the images would be antithetical to that. We don’t save any images you give us or any of the anonymized images created from the AI model (sometimes they’re not perfect, so saving them would still not be great!). If you like technical details: the image is passed into the AI model on the cloud, then the output is passed back and directly displayed in a base64 jpg on your screen.

The bot tweeted my image with the fists on it. Can you take it down? Yes, absolutely. Please DM the bot or reply directly.

Can you talk a bit more about your AI technical approach? We build on state-of-the-art crowd counting AI, because it offers huge advantages to anonymizing crowds over traditional facial recognition models. Traditional methods can only find a few (less than 20 or even less than 5) in a single image. Crowds of BLM protesters can number in the hundreds and thousands, and certainly around 50, in a single image. The model we use in this work has been trained on over 1.2 million people in the open-sourced research dataset, called QNRF, with crowds ranging from the few to the the thousands. False negatives are the worst error in our case. The pretrained model weights live in the LSC-CNN that we build on - precisely, it's in a Google Drive folder linked from their README.

Other amazing tools

We would love to showcase other parallel efforts (please propose any we have missed here!). Not only that, if this is not the tool for you, please check these tools out too:

And more...

Built by and built on

  1. This work is built by the Stanford Machine Learning Group. We are Krishna Patel, JQ, and Sharon Zhou.

  2. Flask-Postgres Template by @sharonzhou

https://github.com/sharonzhou/flask-postgres-template
  1. Image Uploader by @christianbayer
https://github.com/christianbayer/image-uploader
  1. LSC-CNN by @vlad3996
https://github.com/vlad3996/lsc-cnn

Paper associated with this work:

@article{LSCCNN20,
    Author = {Sam, Deepak Babu and Peri, Skand Vishwanath and Narayanan Sundararaman, Mukuntha,  and Kamath, Amogh and Babu, R. Venkatesh},
    Title = {Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection},
    Journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    Year = {2020}
}

Offline mode

See the offline branch to run this work offline using Docker. This awesome code was contributed by @matthiaszimmermann.

Owner
Stanford Machine Learning Group
Our mission is to significantly improve people's lives through our work in AI
Stanford Machine Learning Group
PyTorch Implementation of "Light Field Image Super-Resolution with Transformers"

LFT PyTorch implementation of "Light Field Image Super-Resolution with Transformers", arXiv 2021. [pdf]. Contributions: We make the first attempt to a

Squidward 62 Nov 28, 2022
CMSC320 - Introduction to Data Science - Fall 2021

CMSC320 - Introduction to Data Science - Fall 2021 Instructors: Elias Jonatan Gonzalez and José Manuel Calderón Trilla Lectures: MW 3:30-4:45 & 5:00-6

Introduction to Data Science 6 Sep 12, 2022
VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning

    VarCLR: Variable Representation Pre-training via Contrastive Learning New: Paper accepted by ICSE 2022. Preprint at arXiv! This repository contain

squaresLab 32 Oct 24, 2022
Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes

Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes

111 Dec 29, 2022
Some useful blender add-ons for SMPL skeleton's poses and global translation.

Blender add-ons for SMPL skeleton's poses and trans There are two blender add-ons for SMPL skeleton's poses and trans.The first is for making an offli

犹在镜中 154 Jan 04, 2023
Pixel-wise segmentation on VOC2012 dataset using pytorch.

PiWiSe Pixel-wise segmentation on the VOC2012 dataset using pytorch. FCN SegNet PSPNet UNet RefineNet For a more complete implementation of segmentati

Bodo Kaiser 378 Dec 30, 2022
Pytorch implementation of the unsupervised object discovery method LOST.

LOST Pytorch implementation of the unsupervised object discovery method LOST. More details can be found in the paper: Localizing Objects with Self-Sup

Valeo.ai 189 Dec 25, 2022
This is a beginner-friendly repo to make a collection of some unique and awesome projects. Everyone in the community can benefit & get inspired by the amazing projects present over here.

Awesome-Projects-Collection Quality over Quantity :) What to do? Add some unique and amazing projects as per your favourite tech stack for the communi

Rohan Sharma 178 Jan 01, 2023
Intelligent Video Analytics toolkit based on different inference backends.

English | 中文 OpenIVA OpenIVA is an end-to-end intelligent video analytics development toolkit based on different inference backends, designed to help

Quantum Liu 15 Oct 27, 2022
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

We challenge a common assumption underlying most supervised deep learning: that a model makes a prediction depending only on its parameters and the features of a single input. To this end, we introdu

OATML 360 Dec 28, 2022
Dynamic View Synthesis from Dynamic Monocular Video

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer This repository contains code to compute depth from a

Intelligent Systems Lab Org 2.3k Jan 01, 2023
Official Pytorch Implementation of GraphiT

GraphiT: Encoding Graph Structure in Transformers This repository implements GraphiT, described in the following paper: Grégoire Mialon*, Dexiong Chen

Inria Thoth 80 Nov 27, 2022
Pytorch implementation of the popular Improv RNN model originally proposed by the Magenta team.

Pytorch Implementation of Improv RNN Overview This code is a pytorch implementation of the popular Improv RNN model originally implemented by the Mage

Sebastian Murgul 3 Nov 11, 2022
DeepSpamReview: Detection of Fake Reviews on Online Review Platforms using Deep Learning Architectures. Summer Internship project at CoreView Systems.

Detection of Fake Reviews on Online Review Platforms using Deep Learning Architectures Dataset: https://s3.amazonaws.com/fast-ai-nlp/yelp_review_polar

Ashish Salunkhe 37 Dec 17, 2022
Junction Tree Variational Autoencoder for Molecular Graph Generation (ICML 2018)

Junction Tree Variational Autoencoder for Molecular Graph Generation Official implementation of our Junction Tree Variational Autoencoder https://arxi

Wengong Jin 418 Jan 07, 2023
The Power of Scale for Parameter-Efficient Prompt Tuning

The Power of Scale for Parameter-Efficient Prompt Tuning Implementation of soft embeddings from https://arxiv.org/abs/2104.08691v1 using Pytorch and H

Kip Parker 208 Dec 30, 2022
Code for our paper Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

CorDA Code for our paper Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation Prerequisite Please create and activate the follo

Qin Wang 60 Nov 30, 2022
Rotation-Only Bundle Adjustment

ROBA: Rotation-Only Bundle Adjustment Paper, Video, Poster, Presentation, Supplementary Material In this repository, we provide the implementation of

Seong 51 Nov 29, 2022
Providing the solutions for high-frequency trading (HFT) strategies using data science approaches (Machine Learning) on Full Orderbook Tick Data.

Modeling High-Frequency Limit Order Book Dynamics Using Machine Learning Framework to capture the dynamics of high-frequency limit order books. Overvi

Chang-Shu Chung 1.3k Jan 07, 2023
CAMoE + Dual SoftMax Loss (DSL): Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss

CAMoE + Dual SoftMax Loss (DSL): Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss This is official implement of "

程星 87 Dec 24, 2022