Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)

Overview

Certified Robustness to Adversarial Word Substitutions

This is the official GitHub repository for the following paper:

Certified Robustness to Adversarial Word Substitutions.
Robin Jia, Aditi Raghunathan, Kerem Göksel, and Percy Liang.
Empirical Methods in Natural Language Processing (EMNLP), 2019.

For full details on reproducing the results, see this Codalab worksheet, which contains all code, data, and experiments from the paper. This GitHub repository serves as an easy way to get started with the code, and has some additional instructions and documentation.

Setup

This code has been tested with python3.6, pytorch 1.3.1, numpy 1.15.4, and NLTK 3.4.

Download data dependencies by running the provided script:

./download_deps.sh

If you already have GloVe vectors on your system, it may be more convenient to comment out the part of download_deps.sh that downloads GloVe, and instead add a symlink to the directory containing the GloVe vectors at data/glove.

Interval Bound Propagation library

We have implemented many primitives for Interval Bound Propagation (IBP), which can be found in src/ibp.py. This code should be reusable and intuitive for anyone familiar with pytorch. When designing this library, our goal was to make it possible to write code that looks like standard pytorch code, but can be trained with IBP. Below, we give an overview of the code.

BoundedTensor

BoundedTensor is our version of torch.Tensor. It represents a tensor that additionally has some bounded set of possible values. The two most important subclasses of BoundedTensor are IntervalBoundedTensor and DiscreteChoiceTensor.

IntervalBoundedTensor

An IntervalBoundedTensor keeps track of three instance variables: an actual value, a coordinate-wise upper bound on the value, and a coordinate-wise lower bound on the value. All three of these are torch.Tensor objects. It also implements many standard methods of torch.Tensor.

DiscreteChoiceTensor

A DiscreteChoiceTensor represents a tensor that can take a discrete set of values. We use DiscreteChoiceTensor to represent the set of possible word vectors that can appear at each slice of the input. Importantly, DiscreteChoiceTensor.to_interval_bounded() converts a DiscreteChoiceTensor to an IntervalBoundedTensor by taking a coordinate-wise min/max.

NormBallTensor

We also provide NormBallTensor, which represents a p-norm ball of a given radius around a value.

Functions and layers

To go with BoundedTensor, we include functions and layers that know how to take BoundedTensor objects as inputs and return BoundedTensor objects as outputs. Most of these should be straightforward to use for folks familiar with their standard torch, torch.nn, and torch.nn.functional equivalents (with a caveat that not all flags in the standard library are necessarily supported).

Functions

Available implementations of basic torch functions include:

  • add
  • mul
  • div
  • bmm
  • cat
  • stack
  • sum

In many cases, we directly call the torch counterpart if the inputs are torch.Tensor objects. A few additional cases are described below.

Activation functions

Since monotonic functions all use the same IBP formula, we export a single function ibp.activation which can apply elementwise ReLU, sigmoid, tanh, or exp to an IntervalBoundedTensor.

Logsoftmax

We include a log_softmax() function that is equivalent to torch.nn.functional.log_softmax(). We strongly advise users to use this implementation rather than implementing their own softmax operation, as numerical instability can easily arise with a naive implementation.

Nonnegative matrix multiplication

We include matmul_nneg() function that handles matrix multiplication between two non-negative matrices, as this is simpler than the general case.

Layers (nn.Module objects)

Many basic layers are implemented by extending their torch.nn counterparts, including

  • Linear
  • Embedding
  • Conv1d
  • MaxPool1d
  • LSTM
  • Dropout

RNNs

Our library also includes LSTM and GRU classes, which extend nn.Module directly. These are unfortunately slower than their torch.nn counterparts, because the torch.nn RNN's use cuDNN.

Examples

If you want to see this library in action, a good place to start is BOWModel in src/text_classification.py. This implements a simple bag-of-words model for text classification. Note that in forward(), we accept a flag called compute_bounds which lets the user decide whether to run IBP or not.

Paper experiments

In this repository, we include a minimal set of commands and instructions to reproduce a few key results from our EMNLP 2019 paper. We will focus on the CNN model results on the IMDB dataset. To see other available command line flags, you can run python src/train.py -h.

If you are interested in reproducing our experiments, we recommend looking at the aforementioned Codalab worksheet, which shows how to reproduce all results in our paper. Note that the commands on Codalab include some extra flags (--neighbor-file, --glove-dir, --imdb-dir, and --snli-dir) that are used to specify non-default paths to files. These flags are unnecessary when following the instructions in this repository.

Training

Here are commands to train the CNN model on IMDB with standard training, certifiably robust training, and data augmentation.

Standard training

To train the baseline model without IBP, run the following:

python src/train.py classification cnn outdir_cnn_normal -d 100 --pool mean -T 10 --dropout-prob 0.2 -b 32 --save-best-only

This should get about 88% accuracy on dev (but 0% certified accuracy). outdir_cnn_normal is an output directory where model parameters and stats will be saved.

Certifiably robust training

To use certifiably robust training with IBP, run the following:

python src/train.py classification cnn outdir_cnn_cert -d 100 --pool mean -T 60 --full-train-epochs 20 -c 0.8 --dropout-prob 0.2 -b 32 --save-best-only

This should get about 81% accuracy and 66% certified accuracy on dev. Note that these results do not include language model constraints on the attack surface, and therefore the certified accuracy is a bit too low. These constraints will be enforced in the testing commands below.

Training with data augmentation

To train with data augmentation, run the following:

python src/train.py classification cnn outdir_cnn_aug -d 100 --pool mean -T 60 --augment-by 4 --dropout-prob 0.2 -b 32 --save-best-only

This should get about 85% accuracy and 84% augmented accuracy on dev (but 0% certified accuracy).

Testing

Next, we will show how to test the trained models using the genetic attack. The genetic attack heuristically searches for a perturbation that causes an error. In this phase, we also incorporate pre-computed language model scores that determine which perturbations are valid.

For example, let's say we want to use the trained model inside the outdir_cnn_cert directory. First, we choose a checkpoint based on the best certified accuracy on the dev set, say checkpoint 57. (Note: the training code with --save-best-only will save only the best model and the final model; stats on all checkpoints are logged in <outdir>/all_epoch_stats.json.)

This command will run the genetic attack:

python src/train.py classification cnn eval_cnn_cert -L outdir_cnn_cert --load-ckpt 57 -d 100 --pool mean -T 0 -b 1 -a genetic --adv-num-epochs 40 --adv-pop-size 60 --use-lm --downsample-to 1000

It should get about 80% standard accuracy, 72.5% certified accuracy, and 73% adversarial accuracy (i.e., accuracy against the genetic attack). For all models, you should find that adversarial accuracy is between standard accuracy and certified accuracy. For IMDB, we downsample to 1000 examples, as the genetic attack is pretty slow; the provided precomputed LM scores (in lm_scores) are only for the first 1000 examples in the train, development, and test sets. For SNLI, we use the entire development and test sets for evaluation.

Note: This code is sensitive to the version of NLTK you use. The LM prediction files provided here should work if you are using the current version of NLTK and have updated your nltk_data directory recently. The experiments on Codalab use an older NLTK version; you can download the LM files from Codalab if you need compatibility with older NLTK versions. NLTK version issues will result in a KeyError with an Unrecognized sentence message.

Running the language model yourself

If you want to precompute language model scores on other data, use the following instructions.

  1. Clone the following git repository:
git clone https://github.com/robinjia/l2w windweller-l2w
  1. Obtain pre-trained parameters and put them in a directory named l2w-params within that repository. Please contact us if you need a copy of the parameters.

  2. Adapt src/precompute_lm_scores.py for your dataset.

Pull sensitive data from users on windows including discord tokens and chrome data.

⭐ For a 🍪 Pegasus Pull sensitive data from users on windows including discord tokens and chrome data. Features 🟩 Discord tokens 🟩 Geolocation data

Addi 44 Dec 31, 2022
Adjusting for Autocorrelated Errors in Neural Networks for Time Series

Adjusting for Autocorrelated Errors in Neural Networks for Time Series This repository is the official implementation of the paper "Adjusting for Auto

Fan-Keng Sun 51 Nov 05, 2022
Read and write layered TIFF ImageSourceData and ImageResources tags

Read and write layered TIFF ImageSourceData and ImageResources tags Psdtags is a Python library to read and write the Adobe Photoshop(r) specific Imag

Christoph Gohlke 4 Feb 05, 2022
i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery

i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery This is a public code repository for the publication: i-SpaSP: Structured Neural Pruning

Cameron Ronald Wolfe 5 Nov 04, 2022
Zero-shot Synthesis with Group-Supervised Learning (ICLR 2021 paper)

GSL - Zero-shot Synthesis with Group-Supervised Learning Figure: Zero-shot synthesis performance of our method with different dataset (iLab-20M, RaFD,

Andy_Ge 62 Dec 21, 2022
MediaPipe is a an open-source framework from Google for building multimodal

MediaPipe is a an open-source framework from Google for building multimodal (eg. video, audio, any time series data), cross platform (i.e Android, iOS, web, edge devices) applied ML pipelines. It is

Bhavishya Pandit 3 Sep 30, 2022
On-device speech-to-intent engine powered by deep learning

Rhino Made in Vancouver, Canada by Picovoice Rhino is Picovoice's Speech-to-Intent engine. It directly infers intent from spoken commands within a giv

Picovoice 510 Dec 30, 2022
Python scripts for performing stereo depth estimation using the MobileStereoNet model in Tensorflow Lite.

TFLite-MobileStereoNet Python scripts for performing stereo depth estimation using the MobileStereoNet model in Tensorflow Lite. Stereo depth estimati

Ibai Gorordo 4 Feb 14, 2022
Semantic Segmentation Architectures Implemented in PyTorch

pytorch-semseg Semantic Segmentation Algorithms Implemented in PyTorch This repository aims at mirroring popular semantic segmentation architectures i

Meet Shah 3.3k Dec 29, 2022
PyTorch implementation of DeepUME: Learning the Universal Manifold Embedding for Robust Point Cloud Registration (BMVC 2021)

DeepUME: Learning the Universal Manifold Embedding for Robust Point Cloud Registration [video] [paper] [supplementary] [data] [thesis] Introduction De

Natalie Lang 10 Dec 14, 2022
Code for Massive-scale Decoding for Text Generation using Lattices

Massive-scale Decoding for Text Generation using Lattices Jiacheng Xu, Greg Durrett TL;DR: a new search algorithm to construct lattices encoding many

Jiacheng Xu 37 Dec 18, 2022
Jax/Flax implementation of Variational-DiffWave.

jax-variational-diffwave Jax/Flax implementation of Variational-DiffWave. (Zhifeng Kong et al., 2020, Diederik P. Kingma et al., 2021.) DiffWave with

YoungJoong Kim 37 Dec 16, 2022
Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes (CVPR2021)

RSCD (BS-RSCD & JCD) Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes (CVPR2021) by Zhihang Zhong, Yinqiang Zheng, Imari Sato We co

81 Dec 15, 2022
Distance Encoding for GNN Design

Distance-encoding for GNN design This repository is the official PyTorch implementation of the DEGNN and DEAGNN framework reported in the paper: Dista

172 Nov 08, 2022
This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.

Pruning Self-attentions into Convolutional Layers in Single Path This is the official repository for our paper: Pruning Self-attentions into Convoluti

Zhuang AI Group 77 Dec 26, 2022
ManipNet: Neural Manipulation Synthesis with a Hand-Object Spatial Representation - SIGGRAPH 2021

ManipNet: Neural Manipulation Synthesis with a Hand-Object Spatial Representation - SIGGRAPH 2021 Dataset Code Demos Authors: He Zhang, Yuting Ye, Tak

HE ZHANG 194 Dec 06, 2022
LinkNet - This repository contains our Torch7 implementation of the network developed by us at e-Lab.

LinkNet This repository contains our Torch7 implementation of the network developed by us at e-Lab. You can go to our blogpost or read the article Lin

e-Lab 158 Nov 11, 2022
Official implementation for "Style Transformer for Image Inversion and Editing" (CVPR 2022)

Style Transformer for Image Inversion and Editing (CVPR2022) https://arxiv.org/abs/2203.07932 Existing GAN inversion methods fail to provide latent co

Xueqi Hu 153 Dec 02, 2022
Winners of DrivenData's Overhead Geopose Challenge

Winners of DrivenData's Overhead Geopose Challenge

DrivenData 22 Aug 04, 2022
Development Kit for the SoccerNet Challenge

SoccerNetv2-DevKit Welcome to the SoccerNet-V2 Development Kit for the SoccerNet Benchmark and Challenge. This kit is meant as a help to get started w

Silvio Giancola 117 Dec 30, 2022