nlp_adversarial_examples

KO | EN

gitlite — search

#hacktoberfest #ai #llm #rust #deep-learning #linux #docker #nodejs #macos #cli #vue #pytorch #mcp #ios

nlp_adversarial_examples

(★ 171)

Implementation code for the paper "Generating Natural Language Adversarial Examples"

파일 탐색기

최종 버전 다운로드 (.zip)

.gitignore
attacks.py
BaselineDemo.ipynb
build_embeddings.py
compute_dist_mat.py
data_utils.py
display_utils.py
download_counterfitted_vectors.sh
download_dataset.sh
download_glove.sh
download_googlm.sh
download_snli_data.sh
glove_utils.py
goog_lm.py
IMDB_AttackDemo.ipynb
LICENSE
lm_data_utils.py
lm_utils.py
models.py
NLI_AttackDemo.ipynb
nli_compute_dist_matrix.py
README.md
snli_rnn.py
train_model.py
VisualizeResults.ipynb

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

1) Download the Imdb dataset
```
./download_dataset.sh
```

2) Download the glove vector embeddings (used by the model)
```
 ./download_glove.sh 
```

3) Download the counter-fitted vectors (used by our attack)
```
./download_counterfitted_vectors.sh 
```

4) Build the vocabulary and embeddings matrix.
```
python build_embeddings.py
```

That will take like a minute, and it will tokenize the dataset and save it to a pickle file. It will also compute some auxiliary files like the matrix of the vector embeddings for words in our dictionary. All files will be saved under `aux_files` directory created by this script.

5) Train the sentiment analysis model.
```
python train_model.py
```

6)Download the Google language model.
```
./download_googlm.sh
```

7) Pre-compute the distances between embeddings of different words (required to do the attack) and save the distance matrix.

```
python compute_dist_mat.py

```
8) Now, we are ready to try some attacks ! You can do so by running the [`IMDB_AttackDemo.ipynb`](IMDB_AttackDemo.ipynb) Jupyter notebook !

### Attacking Textual Entailment model

The model we are using for our experiment is the SNLI model of [Keras SNLI Model](https://github.com/Smerity/keras_snli) .

First, Download the dataset using 
```
bash download_snli_data.sh
```

Download the Glove and Counter-fitted Glove embedding vectors

```
bash ./download_glove.sh
bash ./download_counterfitted_vectors.sh
```

Train the NLI model
```
python sni_rnn.py
```

Pre-compute the embedding matrix 
```
python nli_compute_dist_matrix.py
```

Now, you are ready to run the attack using example code provided in [`NLI_AttackDemo.ipynb`](NLI_AttackDemo.ipynb) Jupyter notebook.

nlp_adversarial_examples

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

nlp_adversarial_examples

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README