The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Open accessAbstract
Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness of these models by exposing the maliciously crafted adversarial examples. In this paper, we present TextFooler, a simple but strong baseline to generate adversarial text. By applying it to two fundamental natural language tasks, text classification and textual entailment, we successfully attacked three target models, including the powerful pre-trained BERT, and the widely used convolutional and recurrent neural networks. We demonstrate three advantages of this framework: (1) effective—it outperforms previous attacks by success rate and perturbation rate, (2) utility-preserving—it preserves semantic content, grammaticality, and correct types classified by humans, and (3) efficient—it generates adversarial text with computational complexity linear to the text length.1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071
Convolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Adversarial examples in the physical world
Kurakin, A., Goodfellow, I. J., & Bengio, S. (2018) · Artificial Intelligence Safety and Security · doi:10.1201/9781351251389-8 · Cited by 5,375
Practical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
A large annotated corpus for learning natural language inference
Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1075 · Cited by 3,377
Cited by
Explainable AI: a review of machine learning interpretability methods
Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020) · Entropy · doi:10.3390/e23010018 · Cited by 2,922
“…which follows the synonyms substitution strategy, but replaces words that are based on the word saliency and classification probability TextFooler [161] generates adversarial examples for text by utilising word embedding distance and part-of-speech matching to first identify the most important…”
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Text Data Augmentation for Deep Learning
Shorten, C., Khoshgoftaar, T. M., & Furht, B. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00492-0 · Cited by 1,740
Pre-trained models for natural language processing: A survey
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1647-3 · Cited by 1,591
Pre-trained models: Past, present and future
Han, X., Zhang, Z., Ding, N., Gu, Y., Liu, X., Huo, Y., Qiu, J., Yao, Y., Zhang, A., Zhang, L., et al. (2021) · AI Open · doi:10.1016/j.aiopen.2021.08.002 · Cited by 994
The Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972
The rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
“Researchers have found that pre-trained language models (PLMs) are particularly susceptible to adversarial attacks, leading to erroneous answers [507,516,517].”
Shen, X., Chen, Z., Backes, M., Shen, Y., & Zhang, Y. (2023) · arXiv · doi:10.48550/arxiv.2308.03825 · Cited by 861
ChatGPT and Open-AI Models: A Preliminary Review
Roumeliotis, K. I., & Tselikas, N. D. (2023) · Future Internet · doi:10.3390/fi15060192 · Cited by 706
Explainability for Large Language Models: A Survey
Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639372 · Cited by 681
“More advanced token-level perturbation methods like TextFooler [Jin et al. 2020] have been advanced, which strategically target important words first based on ranking.”
MethodA comprehensive survey on pretrained foundation models: a history from BERT to ChatGPT
Zhou, C., Li, Q., Li, C., Yu, J., Liu, Y., Wang, G., Zhang, K., Ji, C., Yan, Q., He, L., et al. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02443-6 · Cited by 557
BAE: BERT-based Adversarial Examples for Text Classification
Garg, S., & Ramakrishnan, G. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.498 · Cited by 478
Comparing BERT against traditional machine learning text classification
González-Carvajal, S., & Garrido-Merchán, E. C. (2020) · arXiv · doi:10.48550/arxiv.2005.13012 · Cited by 466
Shen, X., Chen, Z., Backes, M., Shen, Y., & Zhang, Y. (2024) · Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3658644.3670388 · Cited by 441
“Besides jailbreak attacks, language models also face other attacks, such as prompt injection [34, 55], backdoor [21, 27], data extraction [26, 44], obfuscation [39], membership inference [50, 66], and adversarial attacks [25, 38, 71].”
COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification
Samuel, J., Ali, G. G. M. N., Rahman, M. M., Esawi, E., & Samuel, Y. (2020) · Information · doi:10.3390/info11060314 · Cited by 407
Deep Learning Based Text Classification: A Comprehensive Review
Minaee, S., Kalchbrenner, N., Cambria, E., Nikzad, N., Asgari-Chenaghlu, M., & Gao, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03705 · Cited by 381
Can Large Language Models Be an Alternative to Human Evaluations?
Chiang, C.-H., & Lee, H.-Y. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.870 · Cited by 331
Can Large Language Models Be an Alternative to Human Evaluations?
Chiang, C.-H., & Lee, H.-Y. (2023) · arXiv · doi:10.48550/arxiv.2305.01937 · Cited by 331
Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
Matsubara, Y., Levorato, M., & Restuccia, F. (2023) · ACM Computing Surveys · doi:10.1145/3527155 · Cited by 304
AMMU: A survey of transformer-based biomedical pretrained language models
Kalyan, K. S., Rajasekharan, A., & Sangeetha, S. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2021.103982 · Cited by 278
A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios
Hedderich, M. A., Lange, L., Adel, H., Strötgen, J., & Klakow, D. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.201 · Cited by 260
A Survey on Text Classification Algorithms: From Text to Predictions
Gasparetto, A., Marcuzzo, M., Zangari, A., & Albarelli, A. (2022) · Information · doi:10.3390/info13020083 · Cited by 253
Natural Attack for Pre-trained Models of Code
Yang, Z., Shi, J., He, J., & Lo, D. (2022) · Proceedings of the 44th International Conference on Software Engineering · doi:10.1145/3510003.3510146 · Cited by 166
Shortcut Learning of Large Language Models in Natural Language Understanding
Du, M., He, F., Zou, N., Tao, D., & Hu, X. (2024) · Communications of the ACM · doi:10.1145/3596490 · Cited by 94
Adversarial attack and defense technologies in natural language processing: A survey
Qiu, S., Liu, Q., Zhou, S., & Huang, W. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.020 · Cited by 94
Sentiment spin: Attacking financial sentiment with GPT-3
Leippold, M. (2023) · Finance Research Letters · doi:10.1016/j.frl.2023.103957 · Cited by 78
DynaSent: A Dynamic Benchmark for Sentiment Analysis
Potts, C., Wu, Z., Geiger, A., & Kiela, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.186 · Cited by 56
Grey-box Adversarial Attack And Defence For Sentiment Classification
Xu, Y., Zhong, X., Jimeno Yepes, A., & Lau, J. H. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.321 · Cited by 54
ReCode: Robustness Evaluation of Code Generation Models
Wang, S., Li, Z., Qian, H., Yang, C., Wang, Z., Shang, M., Kumar, V., Tan, S., Ray, B., Bhatia, P., et al. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.773 · Cited by 42
Yoo, K., Kim, J., Jang, J., & Kwak, N. (2022) · Findings of the Association for Computational Linguistics: ACL 2022 · doi:10.18653/v1/2022.findings-acl.289 · Cited by 33
Red Teaming Language Model Detectors with Language Models
Shi, Z., Wang, Y., Yin, F., Chen, X., Chang, K.-W., & Hsieh, C.-J. (2023) · arXiv · doi:10.48550/arxiv.2305.19713 · Cited by 30
CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
Ning, L.-B., Wang, S., Fan, W., Li, Q., Xu, X., Chen, H., & Huang, F. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671837 · Cited by 22
Improving the robustness and accuracy of biomedical language models through adversarial training
Moradi, M., & Samwald, M. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2022.104114 · Cited by 18
Is Multi-Modal Necessarily Better? Robustness Evaluation of Multi-Modal Fake News Detection
Chen, J., Jia, C., Zheng, H., Chen, R., & Fu, C. (2023) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2023.3249290 · Cited by 17
“Since spelling errors were easy to detect and correct, Jin et al. [49] proposed a black-box attack method TextFooler, which performed synonym substitution for important words and checked the semantic similarity of sentences to fool the system.”
MethodPoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
Zou, W., Geng, R., Wang, B., & Jia, J. (2024) · arXiv · doi:10.48550/arxiv.2402.07867 · Cited by 16
“Here we also evaluate the effectiveness of PoisonedRAG when using TextFooler [76], which replaces words with their synonyms to keep semantics meaning.”
MethodDamacena Duarte, J., Cândido, G. D., De Britto Filho, J. R. A., Souza Neto, J., Da Costa, E. J., Da Costa, J. P. J., & Peotta De Melo, L. (2026) · IEEE Access · doi:10.1109/access.2026.3656849 · Cited by 15
Robustness of generative AI detection: adversarial attacks on black-box neural text detectors
Fishchuk, V., & Braun, D. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-024-10144-2 · Cited by 7
“While watermarking techniques to identify AI-generated texts are also investigated, they are generally seen as vulnerable to adversarial attacks, especially to mutation and paraphrasing-based approaches (Jin et al., 2019; Kirchen-bauer et al., 2023; Sadasivan et al., 2023).”
Lin, T.-L., Chen, W.-C., Hsiao, T.-F., Liu, H.-I., Yeh, Y.-H., Chan, Y.-K., Lien, W.-S., Kuo, P.-Y., Yu, P. S., & Shuai, H.-H. (2025) · Findings of the Association for Computational Linguistics: EMNLP 2025 · doi:10.18653/v1/2025.findings-emnlp.259 · Cited by 6
YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering
D'Souza, J., Giglou, H. B., & Münch, Q. (2025) · arXiv · doi:10.48550/arxiv.2505.14279
“…attacks involves synonym substitution attacks (SSAs) (Alzantot et al., 2018) generate adversarial samples by replacing words with synonyms in benign text, relying on sophisticated methods such as TextFooler (Jin et al., 2020), PWWS (Ren et al., 2019), and BAE (Garg and Ramakrishnan, 2020).”
Chen, Y., Zhang, C., Luo, D., D'Haro, L. F., Tan, R. T., & Li, H. (2024) · arXiv · doi:10.48550/arxiv.2405.14646
In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT
Shen, X., Chen, Z., Backes, M., & Zhang, Y. (2023) · arXiv · doi:10.48550/arxiv.2304.08979 · Cited by 76
“However, once we modify “assists” to “assist” (TextFooler attack), ChatGPT goes for (D) conquer.”
InfluentialGradient-based adversarial attacks against text transformers
Guo, C., Sablayrolles, A., Jégou, H., & Kiela, D. (2021) · arXiv · doi:10.48550/arxiv.2104.13733
Metadata
- Authors
- Jin, D., Jin, Z., Zhou, J. T., & Szolovits, P.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2020-04-03
- Volume
- 34
- Issue
- 05
- Pages
- 8018-8025
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2996851481
- Cited by
- 918
- References
- 31
- FWCI
- 56.04
- Type
- conference paper
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.