BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
Deep neural networks (DNNs) have progressed rapidly during the past decade and have been deployed in various real-world applications. Meanwhile, DNN models have been shown to be vulnerable to security and privacy attacks. One such attack that has attracted a great deal of attention recently is the backdoor attack. Specifically, the adversary poisons the target model’s training set to mislead any input with an added secret trigger to a target class.
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
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, N., & Gurevych, I. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1410 · Cited by 12,778 · cited 2×
“We utilize Sentence-BERT [31] to generate sentence embeddings.”
MethodRecursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · cited 1×
“For instance, multiple works have explored the security and privacy threats of data used to train DNNmodels, such as membership inference attack [30, 35, 36], dataset reconstruction attack [33], and property inference attack [8, 12].”
BackgroundTrojaning Attack on Neural Networks
Liu, Y., Ma, S., Aafer, Y., Lee, W.-C., Zhai, J., Wang, W., & Zhang, X. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23291 · Cited by 1,270
Self-citationCer, D., Yang, Y., Kong, S.-Y., Hua, N., Limtiaco, N., John, R. S., Constant, N., Guajardo-Cespedes, M., Yuan, S., Tar, C., et al. (2018) · arXiv · doi:10.48550/arxiv.1803.11175 · Cited by 1,267
Ganju, K., Wang, Q., Yang, W., Gunter, C. A., & Borisov, N. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243834 · Cited by 475 · cited 1×
“For instance, multiple works have explored the security and privacy threats of data used to train DNNmodels, such as membership inference attack [30, 35, 36], dataset reconstruction attack [33], and property inference attack [8, 12].”
BackgroundPRADA: Protecting Against DNN Model Stealing Attacks
Juuti, M., Szyller, S., Marchal, S., & Asokan, N. (2019) · 2019 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2019.00044 · Cited by 440 · cited 1×
“Other works have explored the threats of models themselves like backdoor attack [10, 34, 41, 42] andmodel stealing attack [13, 24, 39, 40, 43].”
BackgroundWeight Poisoning Attacks on Pretrained Models
Kurita, K., Michel, P., & Neubig, G. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.249 · Cited by 354
Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning
Salem, A., Bhattacharya, A., Backes, M., Fritz, M., & Zhang, Y. (2020) · Universität des Saarlandes · doi:10.22028/d291-47370 · Cited by 157
Self-citation“Transforming” Delete, Retrieve, Generate Approach for Controlled Text Style Transfer
Sudhakar, A., Upadhyay, B., & Maheswaran, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1322 · Cited by 142
Hidden Backdoors in Human-Centric Language Models
Li, S., Liu, H., Dong, T., Zhao, B. Z. H., Xue, M., Zhu, H., & Lu, J. (2021) · Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3460120.3484576 · Cited by 119 · cited 1×
“[17] leveraged LSTM-Beam Search and PPLM to generate dynamic poisoned sentences.”
BackgroundHidden Trigger Backdoor Attacks
Saha, A., Subramanya, A., & Pirsiavash, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6871 · Cited by 13
Cited by
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
“There are also some relevant attack methods such as dataset poisoning [520], backdoor attacks [521,522], and prompt-specific attacks [523,524], with the potential to induce LLMs to generate toxic content [525–527].”
Shen, X., Chen, Z., Backes, M., Shen, Y., & Zhang, Y. (2023) · arXiv · doi:10.48550/arxiv.2308.03825 · Cited by 861
Self-citationLi, Y., Jiang, Y., Li, Z., & Xia, S.-T. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3182979 · Cited by 682
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].”
Self-citation
Metadata
- Authors
- Chen, X., Salem, A., Chen, D., Backes, M., Ma, S., Shen, Q., Wu, Z., & Zhang, Y.
- Venue
- Annual Computer Security Applications Conference
- Publisher
- ACM
- Published
- 2021-12-06
- Pages
- 554-569
- ISSN
- 1063-9527 (ISSN-L)
- OpenAlex
- W3204619801
- Cited by
- 191
- References
- 16
- FWCI
- 12.22
- Type
- conference paper
- Language
- en
- Open access
- green
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.