This is the code for our paper https://arxiv.org/abs/1801.07175
We are focusing on generate adversarial texts for text classification models. However, our framework can be easily extended to other text models. Basically we search for potential adversarials in the text/character embedding space, and reconstruct the texts by nearest neighbor search. The reconstructed texts are verified against the target model to filter out unsuccessful adversarial samples. Searching for potential adversarials in the embedding space is the same as generating adversarial images.
The code to reproduce the results in our paper resides in src/ directory. Our codes are carefully optimized and modularized to make it easy to reuse. Please refer to the README in sub-folder for details.
More results on https://gongzhitaao.org/adversarial-text.