ACL Findings2023
Are Synonym Substitution Attacks Really Synonym Substitution Attacks?
David Cheng-Han Chiang, Hung-yi Lee
摘要
In this paper, we explore the following question: Are synonym substitution attacks really synonym substitution attacks (SSAs)? We approach this question by examining how SSAs replace words in the original sentence and show that there are still unresolved obstacles that make current SSAs generate invalid adversarial samples. We reveal that four widely used word substitution methods generate a large fraction of invalid substitution words that are ungrammatical or do not preserve the original sentence's semantics. Next, we show that the semantic and grammatical constraints used in SSAs for detecting invalid word replacements are highly insufficient in detecting invalid adversarial samples.
问 Lune
尽管问,回答会引用原文。
Lune 会读完全文和相关的 Paper,每个回答都附上所依据的原文段落。
引用它的顶会 Paper3
- Automatically Generated Definitions and their utility for Modeling Word MeaningFrancesco Periti, David Alfter, Nina TahmasebiEMNLP 2024 · 2 次引用
- YESciEval: Robust LLM-as-a-Judge for Scientific Question AnsweringJennifer D'Souza, Hamed Babaei Giglou, Quentin MünchACL 2025
- Precise Verification of Transformers Through ReLU-Catalyzed Abstraction RefinementHengjie Liu, Zhenya Zhang, Jianjun ZhaoCAV 2026
它引用的 Paper8
- Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentDi Jin, Zhijing Jin, Joey Tianyi Zhou, Peter SzolovitsAAAI 2020 · 1,333 次引用
- BERT-ATTACK: Adversarial Attack Against BERT Using BERTLinyang Li, Ruotian Ma, Qipeng Guo, Xiangyang Xue 等EMNLP 2020 · 529 次引用
- Towards Improving Adversarial Training of NLP ModelsJin Yong Yoo, Yanjun QiEMNLP Findings 2021 · 94 次引用
- Reevaluating Adversarial Examples in Natural LanguageJohn X. Morris, Eli Lifland, Jack Lanchantin, Yangfeng Ji 等EMNLP Findings 2020 · 93 次引用
- It's Morphin' Time! Combating Linguistic Discrimination with Inflectional PerturbationsSamson Tan, Shafiq R. Joty, Min-Yen Kan, Richard SocherACL 2020 · 88 次引用
相关 Paper
- Evaluating the Validity of Word-level Adversarial Attacks with Large Language ModelsHuichi Zhou, Zhaoyang Wang, Hongtao Wang, Dongping Chen 等ACL Findings 2024 · 6 次引用
- Bigram and Unigram Based Text Attack via Adaptive Monotonic Heuristic SearchXinghao Yang, Weifeng Liu, James Bailey, Dacheng Tao 等AAAI 2021 · 12 次引用
- SSPAttack: A Simple and Sweet Paradigm for Black-Box Hard-Label Textual Adversarial AttackHan Liu, Zhi Xu, Xiaotong Zhang, Xiaoming Xu 等AAAI 2023 · 31 次引用
- Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text ClassificationMaximilian Mozes, Max Bartolo, Pontus Stenetorp, Bennett Kleinberg 等EMNLP 2021 · 8 次引用
- CheckHARD: Checking Hard Labels for Adversarial Text Detection, Prediction Correction, and Perturbed Word SuggestionHoang-Quoc Nguyen-Son, Huy Quang Ung, Seira Hidano, Kazuhide Fukushima 等EMNLP Findings 2022 · 3 次引用
