BERT is Robust! A Case Against Synonym-Based Adversarial Examples in
Text Classification

BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification

15 September 2021

Roger Wattenhofer

Papers citing "BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification"

10 / 10 papers shown

Title
DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization Songyang Gao Shihan Dou Yan Liu Xiao Wang Qi Zhang Zhongyu Wei Jin Ma Yingchun Shan OOD 19 3 0 27 Jun 2023
Enhancing Robustness of AI Offensive Code Generators via Data Augmentation Cristina Improta Pietro Liguori R. Natella B. Cukic Domenico Cotroneo AAML 30 2 0 08 Jun 2023
Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models Pranath Reddy Kumbam Sohaib Uddin Syed Prashanth Thamminedi S. Harish Ian Perera Bonnie J. Dorr AAML 14 1 0 29 May 2023
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework Yangyi Chen Hongcheng Gao Ganqu Cui Lifan Yuan Dehan Kong ... Longtao Huang H. Xue Zhiyuan Liu Maosong Sun Heng Ji AAML ELM 27 6 0 29 May 2023
Can Large Language Models Be an Alternative to Human Evaluations? Cheng-Han Chiang Hung-yi Lee ALM LM&MA 229 572 0 03 May 2023
Identifying Human Strategies for Generating Word-Level Adversarial Examples Maximilian Mozes Bennett Kleinberg Lewis D. Griffin AAML 33 1 0 20 Oct 2022
Are Synonym Substitution Attacks Really Synonym Substitution Attacks? Cheng-Han Chiang Hunghuei Lee AAML 33 5 0 06 Oct 2022
The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail Sam Bowman OffRL 24 45 0 15 Oct 2021
Certified Robustness to Adversarial Word Substitutions Robin Jia Aditi Raghunathan Kerem Göksel Percy Liang AAML 183 291 0 03 Sep 2019
Generating Natural Language Adversarial Examples M. Alzantot Yash Sharma Ahmed Elgohary Bo-Jhang Ho Mani B. Srivastava Kai-Wei Chang AAML 245 914 0 21 Apr 2018