Needle in a Haystack: Decamouflaging Adversarial Examples Using SBERT Embeddings

Natural Language Processing models are vulnerable to adversarial perturbations which can derail the model’s classification ability. Existing works focus on correcting the training data in order to be resilient to these attacks. In this paper, we propose the idea of multi label classification for adversarial attacks. First, we introduce a new anagram based attack into the literature and second, we train our model to learn these representations by adding a novel label to the dataset which is used as a feature for training the model. Our results show that our method succeeds in separating clean samples from adversarial ones without changing the actual data in the process. We conducted our experiments on the internet movie database dataset. Results show that our method makes a model reliable and robust against character-level perturbations.