Adversarial Attacks and Defense on Texts: A Survey
It addresses the issue of adversarial vulnerabilities in text-based deep learning models for researchers and practitioners, but it is incremental as it synthesizes existing work rather than introducing new methods.
This survey tackles the problem of adversarial attacks and defenses on textual data, which has been less studied compared to image and audio domains, by accumulating and analyzing various techniques to provide a comprehensive overview and highlight findings and challenges.
Deep learning models have been used widely for various purposes in recent years in object recognition, self-driving cars, face recognition, speech recognition, sentiment analysis, and many others. However, in recent years it has been shown that these models possess weakness to noises which force the model to misclassify. This issue has been studied profoundly in the image and audio domain. Very little has been studied on this issue concerning textual data. Even less survey on this topic has been performed to understand different types of attacks and defense techniques. In this manuscript, we accumulated and analyzed different attacking techniques and various defense models to provide a more comprehensive idea. Later we point out some of the interesting findings of all papers and challenges that need to be overcome to move forward in this field.