Awesome
- Download the Imdb dataset
./download_dataset.sh
- Download the glove vector embeddings (used by the model)
./download_glove.sh
- Download the counter-fitted vectors (used by our attack)
./download_counterfitted_vectors.sh
- 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.
- Train the sentiment analysis model.
python train_model.py
6)Download the Google language model.
./download_googlm.sh
- Pre-compute the distances between embeddings of different words (required to do the attack) and save the distance matrix.
python compute_dist_mat.py
- Now, we are ready to try some attacks ! You can do so by running the
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 .
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
Jupyter notebook.