TextFirewall: Omni-Defending Against Adversarial Texts in Sentiment Classification
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Access"
DOI: 10.1109/access.2021.3058278
Abstract: Sentiment classification has been broadly applied in real life, such as product recommendation and opinion-oriented analysis. Unfortunately, the widely employed sentiment classification systems based on deep neural networks (DNNs) are susceptible to adversarial attacks with… read more here.
Keywords: sentiment classification; texts; adversarial texts; defending adversarial ... See more keywords
Automatic Generation of Adversarial Readable Chinese Texts
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2022.3164289
Abstract: Natural language processing (NLP) models are known vulnerable to adversarial examples, similar to image processing models. Studying adversarial texts is an essential step to improve the robustness of NLP models. However, existing studies mainly focus… read more here.
Keywords: automatic generation; generation adversarial; generation; detection ... See more keywords
Towards a Robust Deep Neural Network Against Adversarial Texts: A Survey
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Knowledge and Data Engineering"
DOI: 10.1109/tkde.2021.3117608
Abstract: Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are vulnerable to adversarial examples, which cause… read more here.
Keywords: dnn based; adversarial techniques; deep neural; survey ... See more keywords