v1v2v3v4v5v6 (latest)

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

27 July 2019

ArXiv (abs)PDF HTML Github (511★)

Papers citing "Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment"

50 / 567 papers shown

Title
Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition Aaron Reich Jiaao Chen Aastha Agrawal Yanzhe Zhang Diyi Yang AAML 60 5 0 21 Mar 2022
Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model Jiayi Wang Rongzhou Bao Zhuosheng Zhang Hai Zhao AAML 57 4 0 19 Mar 2022
RoMe: A Robust Metric for Evaluating Natural Language Generation Md. Rony Liubov Kovriguina Debanjan Chaudhuri Ricardo Usbeck Jens Lehmann 75 12 0 17 Mar 2022
Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost Lihu Chen Gaël Varoquaux Fabian M. Suchanek 75 15 0 15 Mar 2022
Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers Sahar Sadrizadeh Ljiljana Dolamic P. Frossard AAML 118 10 0 11 Mar 2022
Leashing the Inner Demons: Self-Detoxification for Language Models Canwen Xu Zexue He Zhankui He Julian McAuley 43 27 0 06 Mar 2022
Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation Kiyoon Yoo Jangho Kim Jiho Jang Nojun Kwak 225 41 0 03 Mar 2022
Robust Textual Embedding against Word-level Adversarial Attacks Yichen Yang Xiaosen Wang Kun He AAML 53 17 0 28 Feb 2022
Using calibrator to improve robustness in Machine Reading Comprehension Jing Jin Houfeng Wang AAML 30 0 0 24 Feb 2022
$$\mathcal{Y}$-Tuning: An Efficient Tuning Paradigm for Large-Scale Pre-Trained Models via Label Representation Learning$ $\mathcal{Y}$ -Tuning: An Efficient Tuning Paradigm for Large-Scale Pre-Trained Models via Label Representation Learning Yitao Liu Chen An Xipeng Qiu 93 17 0 20 Feb 2022
Threats to Pre-trained Language Models: Survey and Taxonomy Shangwei Guo Chunlong Xie Jiwei Li Lingjuan Lyu Tianwei Zhang PILM 57 32 0 14 Feb 2022
Using Random Perturbations to Mitigate Adversarial Attacks on Sentiment Analysis Models Abigail Swenor Jugal Kalita AAML 120 12 0 11 Feb 2022
Attacking c-MARL More Effectively: A Data Driven Approach Nhan H. Pham Lam M. Nguyen Jie Chen Hoang Thanh Lam Subhro Das Tsui-Wei Weng AAML 99 2 0 07 Feb 2022
On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks Salijona Dyrmishi Salah Ghamizi Thibault Simonetto Yves Le Traon Maxime Cordy AAML 86 20 0 07 Feb 2022
Identifying Adversarial Attacks on Text Classifiers Zhouhang Xie Jonathan Brophy Adam Noack Wencong You Kalyani Asthana Carter Perkins Sabrina Reis Sameer Singh Daniel Lowd AAML 84 10 0 21 Jan 2022
Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and Adverbs Anna Filighera Sebastian Ochs Tim Steuer Thomas Tregel AAML 48 11 0 20 Jan 2022
TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack Zhen Yu Xiaosen Wang Wanxiang Che Kun He AAML 55 16 0 20 Jan 2022
Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations Chris Emmery Ákos Kádár Grzegorz Chrupała Walter Daelemans 55 5 0 17 Jan 2022
Quantifying Robustness to Adversarial Word Substitutions Yuting Yang Pei Huang Feifei Ma Juan Cao Meishan Zhang Jian Zhang Jintao Li AAML 60 3 0 11 Jan 2022
Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing Lingfeng Shen Haiyun Jiang Lemao Liu Shuming Shi ELM 24 1 0 09 Jan 2022
An Adversarial Benchmark for Fake News Detection Models Lorenzo Jaime Yu Flores Sophie Hao 43 10 0 03 Jan 2022
Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions Marwan Omar Soohyeon Choi Daehun Nyang David A. Mohaisen 78 58 0 03 Jan 2022
On Sensitivity of Deep Learning Based Text Classification Algorithms to Practical Input Perturbations Aamir Miyajiwala Arnav Ladkat Samiksha Jagadale Raviraj Joshi AAML 69 7 0 02 Jan 2022
Repairing Adversarial Texts through Perturbation Guoliang Dong Jingyi Wang Jun Sun Sudipta Chattopadhyay Xinyu Wang Ting Dai Jie Shi J. Dong AAML 32 2 0 29 Dec 2021
Distilling the Knowledge of Romanian BERTs Using Multiple Teachers Andrei-Marius Avram Darius Catrina Dumitru-Clementin Cercel Mihai Dascualu Traian Rebedea Vasile Puaics Dan Tufics 60 12 0 23 Dec 2021
Understanding and Measuring Robustness of Multimodal Learning Nishant Vishwamitra Hongxin Hu Ziming Zhao Long Cheng Feng Luo AAML 86 5 0 22 Dec 2021
Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction Dongfang Li Baotian Hu Qingcai Chen Tujie Xu Jingcong Tao Yunan Zhang 75 12 0 20 Dec 2021
DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models Hongyu Zhu Yan Chen Jing Yang Jing Liu Yu Hong Ying-Cong Chen Hua Wu Haifeng Wang AAML 86 6 0 16 Dec 2021
Adversarial Examples for Extreme Multilabel Text Classification Mohammadreza Qaraei Rohit Babbar 53 6 0 14 Dec 2021
Quantifying and Understanding Adversarial Examples in Discrete Input Spaces Volodymyr Kuleshov Evgenii Nikishin S. Thakoor Tingfung Lau Stefano Ermon AAML 69 1 0 12 Dec 2021
SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization Wenbo Gou Wen Shi Jian Lou Lijie Huang Pan Zhou Ruixuan Li AAML 69 2 0 08 Dec 2021
Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View Di Jin Elena Sergeeva W. Weng Geeticka Chauhan Peter Szolovits OOD 120 58 0 05 Dec 2021
Supporting Undotted Arabic with Pre-trained Language Models Aviad Rom Kfir Bar 43 4 0 18 Nov 2021
Improving the robustness and accuracy of biomedical language models through adversarial training M. Moradi Matthias Samwald AAML OOD MedIm 80 12 0 16 Nov 2021
NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation David Alfonso-Hermelo Ahmad Rashid Abbas Ghaddar Huawei Noah’s Mehdi Rezagholizadeh 77 2 0 09 Nov 2021
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models Wei Ping Chejian Xu Shuohang Wang Zhe Gan Yu Cheng Jianfeng Gao Ahmed Hassan Awadallah Yangqiu Song VLM ELM AAML 78 226 0 04 Nov 2021
Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization Shengcai Liu Ning Lu W. Hong Chao Qian Ke Tang AAML 102 15 0 02 Nov 2021
AdvCodeMix: Adversarial Attack on Code-Mixed Data Sourya Dipta Das Ayan Basak Soumil Mandal Dipankar Das AAML 21 4 0 30 Oct 2021
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework Lifan Yuan Yichi Zhang Yangyi Chen Wei Wei AAML 113 34 0 28 Oct 2021
Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions I. Alsmadi Kashif Ahmad Mahmoud Nazzal Firoj Alam Ala I. Al-Fuqaha Abdallah Khreishah A. Algosaibi AAML 57 16 0 26 Oct 2021
Alignment Attention by Matching Key and Query Distributions Shujian Zhang Xinjie Fan Huangjie Zheng Korawat Tanwisuth Mingyuan Zhou OOD 114 10 0 25 Oct 2021
Text Counterfactuals via Latent Optimization and Shapley-Guided Search Quintin Pope Xiaoli Z. Fern 64 20 0 22 Oct 2021
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer Fanchao Qi Yangyi Chen Xurui Zhang Mukai Li Zhiyuan Liu Maosong Sun AAML SILM 157 186 0 14 Oct 2021
SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text Hoang-Quoc Nguyen-Son Seira Hidano Kazuhide Fukushima S. Kiyomoto AAML 86 0 0 12 Oct 2021
Noisy Text Data: Achilles' Heel of popular transformer based NLP models Kartikay Bagla Ankit Kumar Shivam Gupta Anuj Gupta 51 6 0 07 Oct 2021
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs Philipp Benz Soomin Ham Chaoning Zhang Adil Karjauv In So Kweon AAML ViT 100 80 0 06 Oct 2021
Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models Wenqian Ye Fei Xu Yaojia Huang Cassie Huang A. Ji 27 2 0 03 Oct 2021
Improving Question Answering Performance Using Knowledge Distillation and Active Learning Yasaman Boreshban Seyed Morteza Mirbostani Gholamreza Ghassem-Sani Seyed Abolghasem Mirroshandel Shahin Amiriparian 78 16 0 26 Sep 2021
Breaking BERT: Understanding its Vulnerabilities for Named Entity Recognition through Adversarial Attack A. Dirkson Suzan Verberne Wessel Kraaij SILM 48 4 0 23 Sep 2021
Adversarial Training with Contrastive Learning in NLP Daniela N. Rim DongNyeong Heo Heeyoul Choi AAML 49 14 0 19 Sep 2021