文本对抗之博客列表

Text Adversarial Example Notes List

Text Adv Attack

Text Adv Attack Word Level

1. Text Adv Attack Word Level Note 1

• Crafting Adversarial Input Sequences For Recurrent Neural Networks. Nicolas Papernot, Patrick McDaniel, Ananthram Swami, Richard Harang. MILCOM 2016. RNN, Word, Gradient [ PDF ] [ The Pennsylvania State University ]
• Towards Crafting Text Adversarial Samples. Suranjana Samanta, Sameep Mehta. ECIR 2018. Word, Gradient, Genre [ PDF ] [ IBM India Research Lab (IRL) ]
• Deep Text Classification Can be Fooled. Bin Liang, Hongcheng Li, Miaoqiang Su, Pan Bian, Xirong Li, Wenchang Shi. IJCAI 2018. Gradient, Score , Word&Character, Target [ PDF ] [ Renmin University of China, Beijing ]

2. Text Adv Attack Word Level Note 2

• Breaking NLI Systems with Sentences that Require Simple Lexical Inferences.
  Max Glockner, Vered Shwartz, Yoav Goldberg. ACL 2018. NLI, blind [PDF] [ TU Darmstadt, Germany ]
• Generating Natural Language Adversarial Examples. Moustafa Alzantot, Yash Sharma, Ahmed Elgohary, Bo-Jhang Ho, Mani Srivastava, Kai-Wei Chang. EMNLP 2018. Score GA [ PDF ] [ University of California ]
• Universal Adversarial Attacks on Text Classifiers. Melika Behjati, Seyed-Mohsen Moosavi-Dezfooli, Mahdieh Soleymani Baghshah, Pascal Frossard. ICASSP 2019. Gradient Universal [ PDF ] [ Sharif University of Technology, Tehran, Iran ]

3. Text Adv Attack Word Level Note 3

• Robust Neural Machine Translation with Doubly Adversarial Inputs. Yong Cheng, Lu Jiang, Wolfgang Macherey. ACL 2019. Gradient NMT [ PDF ] [ Google AI ]
• Generating Fluent Adversarial Examples for Natural Languages. Huangzhao Zhang, Hao Zhou, Ning Miao, Lei Li. ACL 2019. Gradient Score [ PDF ] [ Peking University, ByteDance AI Lab ]
• Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency. Shuhuai Ren, Yihe Deng, Kun He, Wanxiang Che. ACL 2019. Score [ PDF ] [ Huazhong University of Science and Technology ]

4. Text Adv Attack Word Level Note 4

• On the Robustness of Self-Attentive Models. Yu-Lun Hsieh, Minhao Cheng, Da-Cheng Juan, Wei Wei, Wen-Lian Hsu, Cho-Jui Hsieh. ACL 2019. Score [ PDF ] [ SNHCC, TIGP, Academia Sinica, Taiwan]

Text Adv Defense

Text Adv Defense Adversarial Training

1. Text Adv Defense Adversarial Training Note 1

• Miyato T, Dai A M, Goodfellow I. Adversarial training methods for semi-supervised text classification[J]. arXiv preprint arXiv:1605.07725, 2016. VAT [ PDF ] [ ICLR 2017 ] [ Google Brain ，OpenAI ]
• Sato M, Suzuki J, Shindo H, et al. Interpretable adversarial perturbation in input embedding space for text[J]. arXiv preprint arXiv:1805.02917, 2018.Interpretability, VAT [ PDF ] [ IJCAI 2018 ] [ IBM India Research Lab ]