paper-with-me

홈 › Papers

Generating Fluent Adversarial Examples for Natural Languages

2020-07-13 · ACL 2019 7 · Huangzhao Zhang, Hao Zhou, Ning Miao, Lei LI

Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge. Firstly, as the sentence space is discrete, it is difficult to make small perturbations along the direction of gradients. Secondly, the fluency of the generated examples cannot be guaranteed. In this paper, we propose MHA, which addresses both problems by performing Metropolis-Hastings sampling, whose proposal is designed with the guidance of gradients. Experiments on IMDB and SNLI show that our proposed MHA outperforms the baseline model on attacking capability. Adversarial training with MAH also leads to better robustness and performance.

📄 PDF Abstract BibTeX arXiv:2007.06174

Code (0)

등록된 구현이 없습니다.

Tasks

Sentence

Similar Papers 제목 키워드 기반

Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces

2020-12-29 · Linyang Li, Yunfan Shao, Demin Song, Xipeng Qiu 외

Adversarial attacks in texts are mostly substitution-based methods that replace words or characters in the original texts to achieve success attacks. Recent methods use pre-trained language models as the substitutes gene…

Language ModelingLanguage ModellingSentence

Contextualized Perturbation for Textual Adversarial Attack

2020-09-16 · NAACL 2021 4 · Dianqi Li, Yizhe Zhang, Hao Peng, Liqun Chen 외

Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness. Existing techniques of generating such examples are typically driven …

Adversarial AttackLanguage ModelingLanguage Modelling

A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples

2020-10-03 · COLING 2020 8 · Zhao Meng, Roger Wattenhofer

Generating adversarial examples for natural language is hard, as natural language consists of discrete symbols, and examples are often of variable lengths. In this paper, we propose a geometry-inspired attack for generat…

R&R: Metric-guided Adversarial Sentence Generation

2021-04-17 · Lei Xu, Alfredo Cuesta-Infante, Laure Berti-Equille, Kalyan Veeramachaneni

Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences t…

Adversarial AttackGeneral ClassificationSemantic SimilaritySemantic Textual Similarity+4

Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning

2019-07-09 · Yu Zhang, Ron J. Weiss, Heiga Zen, Yonghui Wu 외

We present a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages. Moreover, the model is able to transfer voices across lang…

Speech Synthesistext-to-speechText to SpeechVoice Cloning