Initial

.gitignore

@@ -0,0 +1,218 @@
+# File created using '.gitignore Generator' for Visual Studio Code: https://bit.ly/vscode-gig
+
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,macos,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,macos,python
+
+aux_files/
+corpus/
+dumped/
+models/Transformer/en-de-en
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# Support for Project snippet scope
+
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,macos,python
+
+# Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)
+

.vscode/launch.json

@@ -0,0 +1,16 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Current File",
+            "type": "python",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal",
+            "justMyCode": true
+        }
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "cSpell.enabled": false
+}

README.md

@@ -0,0 +1,79 @@
+# Crafting Adversarial Examples for Neural Machine Translation
+
+We provide code for the Paper: *Crafting Adversarial Examples for Neural Machine Translation* \
+Xinze Zhang, Junzhe Zhang, Zhenhua Chen, Kun He
+
+## Introduction
+
+Effective adversary generation for neural machine translation (NMT) is a crucial prerequisite for building robust machine translation systems. In this work, we investigate veritable evaluations of NMT adversarial attacks, and propose a novel method to craft NMT adversarial examples. We propose to leverage the round-trip translation technique to build valid metrics for evaluating NMT adversarial attacks. Our intuition is that an effective NMT adversarial example, which imposes minor shifting on the source and degrades the translation dramatically, would naturally lead to a semantic-destroyed round-trip translation result. We then propose a promising black-box attack method called Word Saliency speedup Local Search (WSLS) that could effectively attack the mainstream NMT architectures.
+
+Our main contributions are as follows:
+
+1) We introduce an appropriate definition of NMT adversary and the deriving evaluation metrics, which are capable of estimating the adversaries only using source information, and tackle well the challenge of missing ground-truth reference after the perturbation.
+
+2) We propose a novel black-box word level NMT attack method that could effectively attack the mainstream NMT models, and exhibit high transferability when attacking popular online translators.
+
+
+## Server Environment
+- Pos_OS 20.04.LTS
+- Python 3.6
+- CUDA >= 10.2
+  - use `cat /usr/lib/cuda/version.txt` to check the cuda version
+- NCCL for fairseq
+  - The official and tested builds of NCCL can be downloaded from: https://developer.nvidia.com/nccl
+- apex for faster training (require RTX-based GPUs)
+  ```
+  git clone https://github.com/NVIDIA/apex
+  cd apex
+  pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" \
+  --global-option="--deprecated_fused_adam" --global-option="--xentropy" \
+  --global-option="--fast_multihead_attn" ./
+  ```
+
+## Requirements
+```
+pickle
+sklearn
+torch
+nltk
+pkuseg
+transformers
+pyltp
+zhon
+spacy
+spacy(en-pipcore-web-sm)
+spacy_cld
+sacremoses
+subword-nmt
+fairseq
+fvcore
+```
+### Installation
+- pickle
+  - default package in the protogenetic conda python env
+- sklearn, nltk, torch
+  ```
+  conda install scikit-learn
+  conda install nltk
+  conda install pytorch cudatoolkit=10.2 -c pytorch
+  ```
+- pkuseg, zhon, spacy, spacy([en-pipcore-web-sm](https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.2.0/en_core_web_sm-2.2.0.tar.gz#egg=en_core_web_sm==2.2.0)), spacy_cld, sacremoses, subword, pyltp (require python = 3.6),transformers (require pytorch), fairseq (require Pytorch >= 1.4.0, Python >= 3.5, Nvidia GPU , and NCCL)
+  ```
+  pip install pkuseg
+  pip install zhon
+  pip install sacremoses
+  pip install subword-nmt
+  pip install pyltp
+  pip install transformers
+  pip install fvcore
+  pip install spacy-cld
+  pip install -U spacy
+  pip install ./aux_files/en_core_web_sm-2.2.0.tar.gz
+
+  cd ..
+  git clone https://github.com/pytorch/fairseq
+  cd fairseq
+  pip install --editable ./
+  ```
+  where  `en_core_web_sm-2.2.0.tar.gz` can be downloaded in the [link](https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.2.0/en_core_web_sm-2.2.0.tar.gz#egg=en_core_web_sm==2.2.0)
+