Adversarial Attacks and Defense on Texts: A Survey
arXiv:2005.14108
Abstract
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.
References in corpus (20)
- A Survey on Deep Learning in Medical Image Analysis
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Generating Natural Adversarial Examples
- Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
- Deep Text Classification Can be Fooled
- Synthetic and Natural Noise Both Break Neural Machine Translation
- Adversarial Examples for Evaluating Reading Comprehension Systems
- Towards Crafting Text Adversarial Samples
- A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
- Deceiving Google's Perspective API Built for Detecting Toxic Comments
- HotFlip: White-Box Adversarial Examples for Text Classification
- Robust Neural Machine Translation with Doubly Adversarial Inputs
- Natural Language Adversarial Defense through Synonym Encoding
- Protecting Voice Controlled Systems Using Sound Source Identification Based on Acoustic Cues
- Towards a Robust Deep Neural Network in Texts: A Survey
- Combating Adversarial Misspellings with Robust Word Recognition
- Robust Machine Comprehension Models via Adversarial Training
- On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models
- White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks
- Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension