Towards Robustness Against Natural Language Word Substitutions

International Conference on Learning Representations (ICLR), 2021

28 July 2021

Papers citing "Towards Robustness Against Natural Language Word Substitutions"

50 / 70 papers shown

Title
Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal Yang Wang Chenghao Xiao Yi Zhou Stuart E. Middleton Noura Al Moubayed C. D. Lin AAML 243 1 0 29 Jul 2025
Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix ApproachAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Mohammed Bouri Adnane Saoud AAML SILM 161 0 0 14 Jul 2025
Rapid Urban Visibility Hotspots: Quantifying Building Vertex Visibility from Connected Vehicle Trajectories using Spatial Indexing Artur Grigorev Adriana-Simona Mihaita 250 0 0 03 Jun 2025
The Counting Power of Transformers Marco Sälzer Chris Köcher Anthony Widjaja Lin Georg Zetzsche Anthony Widjaja Lin 311 1 0 16 May 2025
Model Hemorrhage and the Robustness Limits of Large Language Models Ziyang Ma Hui Yuan Guang Dai Gui-Song Xia Bo Du Liangpei Zhang Dacheng Tao 277 1 0 31 Mar 2025
Confidence Elicitation: A New Attack Vector for Large Language ModelsInternational Conference on Learning Representations (ICLR), 2025 Brian Formento Chuan-Sheng Foo See-Kiong Ng AAML 539 2 0 07 Feb 2025
Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence BenchmarksInternational Conference on Computational Linguistics (COLING), 2025 Yang Wang Chenghua Lin ELM 341 3 0 05 Jan 2025
ProTransformer: Robustify Transformers via Plug-and-Play ParadigmNeural Information Processing Systems (NeurIPS), 2024 Zhichao Hou Weizhi Gao Yuchen Shen Feiyi Wang Xiaorui Liu VLM 217 2 0 30 Oct 2024
A New Benchmark Dataset and Mixture-of-Experts Language Models for Adversarial Natural Language Inference in Vietnamese Tin Van Huynh Kiet Van Nguyen Ngan Luu-Thuy Nguyen 272 2 0 25 Jun 2024
Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning Marco Sälzer Eric Alsmann Martin Lange LRM 109 3 0 28 May 2024
GenFighter: A Generative and Evolutive Textual Attack Removal Md Athikul Islam Edoardo Serra Sushil Jajodia AAML 143 0 0 17 Apr 2024
SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks Brian Formento Wenjie Feng Chuan-Sheng Foo Anh Tuan Luu See-Kiong Ng AAML 265 9 0 27 Mar 2024
Extreme Miscalibration and the Illusion of Adversarial Robustness Vyas Raina Samson Tan Volkan Cevher Aditya Rawal Sheng Zha George Karypis AAML 263 4 0 27 Feb 2024
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning Shuai Zhao Yaoyao Yu Anh Tuan Luu Jie Fu Lingjuan Lyu Meihuizi Jia Jinming Wen AAML 276 29 0 19 Feb 2024
Fast Adversarial Training against Textual Adversarial Attacks Yichen Yang Xin Liu Kun He AAML 150 6 0 23 Jan 2024
Toward Stronger Textual Attack DetectorsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Pierre Colombo Marine Picot Nathan Noiry Guillaume Staerman Pablo Piantanida 778 5 0 21 Oct 2023
Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting Zecheng Tang Kaiqi Feng Juntao Li Min Zhang 200 2 0 20 Oct 2023
Fooling the Textual Fooler via Randomizing Latent RepresentationsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Duy C. Hoang Quang H. Nguyen Saurav Manchanda MinLong Peng Kok-Seng Wong Khoa D. Doan SILM AAML 235 2 0 02 Oct 2023
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLMAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Bochuan Cao Yu Cao Lu Lin Jinghui Chen AAML 407 188 0 18 Sep 2023
LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial AttackAAAI Conference on Artificial Intelligence (AAAI), 2023 HaiXiang Zhu Zhaoqing Yang Weiwei Shang Yuren Wu AAML FAtt 269 14 0 01 Aug 2023
Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial AttacksIEEE Symposium on Security and Privacy (IEEE S&P), 2023 Xinyu Zhang Hanbin Hong Yuan Hong Peng Huang Binghui Wang Zhongjie Ba Kui Ren SILM 318 31 0 31 Jul 2023
Transferable Adversarial Robustness for Categorical Data via Universal Robust EmbeddingsNeural Information Processing Systems (NeurIPS), 2023 Klim Kireev Maksym Andriushchenko Carmela Troncoso Nicolas Flammarion OOD 237 2 0 06 Jun 2023
A Causal View of Entity Bias in (Large) Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Fei Wang Wen-An Mo Yiwei Wang Wenxuan Zhou Muhao Chen 178 20 0 24 May 2023
Randomized Smoothing with Masked Inference for Adversarially Robust Text ClassificationsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Han Cheol Moon Shafiq Joty Ruochen Zhao Megh Thakkar Xu Chi AAML 207 18 0 11 May 2023
Toward Adversarial Training on Contextualized Language RepresentationInternational Conference on Learning Representations (ICLR), 2023 Hongqiu Wu Wenshu Fan Han Shi Haizhen Zhao Hao Fei AAML 134 15 0 08 May 2023
The Best Defense is Attack: Repairing Semantics in Textual Adversarial ExamplesConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Heng Yang Ke Li AAML 271 4 0 06 May 2023
ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification Marco Casadio Luca Arnaboldi M. Daggitt Omri Isac Tanvi Dinkar Daniel Kienitz Verena Rieser Ekaterina Komendantskaya 200 5 0 06 May 2023
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Shuai Zhao Jinming Wen Anh Tuan Luu Jiaqi Zhao Jie Fu SILM 534 123 0 02 May 2023
RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models Seulki Park Daeho Um Hajung Yoon Sanghyuk Chun Sangdoo Yun Hawook Jeong 343 5 0 21 Apr 2023
Masked Language Model Based Textual Adversarial Example DetectionACM Asia Conference on Computer and Communications Security (AsiaCCS), 2023 Xiaomei Zhang Zhaoxi Zhang Qi Zhong Xufei Zheng Yanjun Zhang Shengshan Hu L. Zhang AAML 285 8 0 18 Apr 2023
Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions Marwan Omar SILM AAML 187 21 0 14 Feb 2023
Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend Ning Lu Shengcai Liu Zhirui Zhang Qi. Wang Haifeng Liu Jiaheng Zhang AAML 287 13 0 06 Feb 2023
TextShield: Beyond Successfully Detecting Adversarial Sentences in Text ClassificationInternational Conference on Learning Representations (ICLR), 2023 Lingfeng Shen Ze Zhang Haiyun Jiang Ying-Cong Chen AAML 316 9 0 03 Feb 2023
On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on CodexConference of the European Chapter of the Association for Computational Linguistics (EACL), 2023 Terry Yue Zhuo Zhuang Li Yujin Huang Fatemeh Shiri Weiqing Wang Gholamreza Haffari Yuan-Fang Li AAML 334 64 0 30 Jan 2023
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven OptimizationInternational Conference on Learning Representations (ICLR), 2022 Bairu Hou Jinghan Jia Yihua Zhang Guanhua Zhang Yang Zhang Sijia Liu Shiyu Chang SILM AAML 143 27 0 19 Dec 2022
Preserving Semantics in Textual Adversarial AttacksEuropean Conference on Artificial Intelligence (ECAI), 2022 David Herel Hugo Cisneros Tomas Mikolov AAML 197 8 0 08 Nov 2022
Textual Manifold-based Defense Against Natural Language Adversarial ExamplesConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 D. M. Nguyen Anh Tuan Luu AAML 245 24 0 05 Nov 2022
Emergent Linguistic Structures in Neural Networks are Fragile Emanuele La Malfa Matthew Wicker Marta Kiatkowska 469 1 0 31 Oct 2022
Disentangled Text Representation Learning with Information-Theoretic Perspective for Adversarial RobustnessIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2022 Jiahao Zhao Wenji Mao DRL OOD 132 7 0 26 Oct 2022
TCAB: A Large-Scale Text Classification Attack Benchmark Kalyani Asthana Zhouhang Xie Wencong You Adam Noack Jonathan Brophy Sameer Singh Daniel Lowd 289 3 0 21 Oct 2022
Probabilistic Categorical Adversarial Attack & Adversarial Training Han Xu Penghei He Jie Ren Yuxuan Wan Zitao Liu Hui Liu Shucheng Zhou AAML SILM 168 1 0 17 Oct 2022
Rethinking Textual Adversarial Defense for Pre-trained Language ModelsIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2022 Jiayi Wang Rongzhou Bao Zhuosheng Zhang Hai Zhao AAML SILM 185 14 0 21 Jul 2022
Certified Robustness Against Natural Language Attacks by Causal InterventionInternational Conference on Machine Learning (ICML), 2022 Haiteng Zhao Chang Ma Xinshuai Dong Anh Tuan Luu Zhi-Hong Deng Hanwang Zhang AAML 246 40 0 24 May 2022
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 Yong Xie Dakuo Wang Pin-Yu Chen Jinjun Xiong Sijia Liu Oluwasanmi Koyejo AAML 250 26 0 01 May 2022
Improving robustness of language models from a geometry-aware perspectiveFindings (Findings), 2022 Bin Zhu Zhaoquan Gu Le Wang Jinyin Chen Qi Xuan AAML 104 10 0 28 Apr 2022
"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial AttacksAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Edoardo Mosca Shreyash Agarwal Javier Rando Georg Groh AAML 186 39 0 10 Apr 2022
Text Adversarial Purification as Defense against Adversarial AttacksAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Linyang Li Demin Song Xipeng Qiu AAML 136 19 0 27 Mar 2022
Adversarial Training for Improving Model Robustness? Look at Both Prediction and InterpretationAAAI Conference on Artificial Intelligence (AAAI), 2022 Hanjie Chen Yangfeng Ji OOD AAML VLM 177 25 0 23 Mar 2022
On Robust Prefix-Tuning for Text ClassificationInternational Conference on Learning Representations (ICLR), 2022 Zonghan Yang Yang Liu VLM 151 22 0 19 Mar 2022
A Survey of Adversarial Defences and Robustness in NLP Shreyansh Goyal Sumanth Doddapaneni Mitesh M.Khapra B. Ravindran AAML 379 35 0 12 Mar 2022