Improving robustness of language models from a geometry-aware
perspective

Improving robustness of language models from a geometry-aware perspective

28 April 2022

ArXiv (abs)PDF HTML

Papers citing "Improving robustness of language models from a geometry-aware perspective"

15 / 15 papers shown

Title
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution Zongyi Li Jianhan Xu Jiehang Zeng Linyang Li Xiaoqing Zheng Qi Zhang Kai-Wei Chang Cho-Jui Hsieh AAML 46 74 0 29 Aug 2021
Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning Chenglei Si Zhengyan Zhang Fanchao Qi Zhiyuan Liu Yasheng Wang Qun Liu Maosong Sun AAML SILM 83 69 0 31 Dec 2020
Geometry-aware Instance-reweighted Adversarial Training Jingfeng Zhang Jianing Zhu Gang Niu Bo Han Masashi Sugiyama Mohan Kankanhalli AAML 53 278 0 05 Oct 2020
DeBERTa: Decoding-enhanced BERT with Disentangled Attention Pengcheng He Xiaodong Liu Jianfeng Gao Weizhu Chen AAML 165 2,750 0 05 Jun 2020
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger Jingfeng Zhang Xilie Xu Bo Han Gang Niu Li-zhen Cui Masashi Sugiyama Mohan S. Kankanhalli AAML 56 404 0 26 Feb 2020
FreeLB: Enhanced Adversarial Training for Natural Language Understanding Chen Zhu Yu Cheng Zhe Gan S. Sun Tom Goldstein Jingjing Liu AAML 282 442 0 25 Sep 2019
Certified Robustness to Adversarial Word Substitutions Robin Jia Aditi Raghunathan Kerem Göksel Percy Liang AAML 337 294 0 03 Sep 2019
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment Di Jin Zhijing Jin Qiufeng Wang Peter Szolovits SILM AAML 185 1,086 0 27 Jul 2019
TextBugger: Generating Adversarial Text Against Real-world Applications Jinfeng Li S. Ji Tianyu Du Bo Li Ting Wang SILM AAML 211 743 0 13 Dec 2018
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding Alex Jinpeng Wang Amanpreet Singh Julian Michael Felix Hill Omer Levy Samuel R. Bowman ELM 1.1K 7,196 0 20 Apr 2018
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 317 12,131 0 19 Jun 2017
Crafting Adversarial Input Sequences for Recurrent Neural Networks Nicolas Papernot Patrick McDaniel A. Swami Richard E. Harang AAML GAN SILM 51 456 0 28 Apr 2016
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 282 19,121 0 20 Dec 2014
Convolutional Neural Networks for Sentence Classification Yoon Kim AILaw VLM 641 13,432 0 25 Aug 2014
Intriguing properties of neural networks Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna D. Erhan Ian Goodfellow Rob Fergus AAML 282 14,963 1 21 Dec 2013