WordsWorth Scores for Attacking CNNs and LSTMs for Text Classification

Nimrah Shakeel

Abstract: Black box attacks on traditional deep learning models trained for text classifica- tion target important words in a piece of text, in order to change model prediction. Current approaches towards highlighting important features are time consuming and require large number of model queries. We present a simple yet novel method to calculate word importance scores, based on model predictions on single words. These scores, which we call WordsWorth scores, need to be calculated only once for the training vocabulary. They can be used to speed up any attack method that requires word importance, with negligible loss of attack performance. We run ex- periments on a number of datasets trained on word-level CNNs and LSTMs, for sentiment analysis and topic classification and compare to state-of-the-art base- lines. Our results show the effectiveness of our method in attacking these models with success rates that are close to the original baselines. We argue that global importance scores act as a very good proxy for word importance in a local context because words are a highly informative form of data. This aligns with the manner in which humans interpret language, with individual words having well- defined meaning and powerful connotations. We further show that these scores can be used as a debugging tool to interpret a trained model by highlighting rele- vant words for each class. Additionally, we demonstrate the effect of overtraining on word importance, compare the robustness of CNNs and LSTMs, and explain the transferability of adversarial examples across a CNN and an LSTM using these scores. We highlight the fact that neural networks make highly informative pre- dictions on single words.

One-sentence Summary: An efficient method for computing word importance scores for CNNs and LSTMs

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=g7SM7Ny8k