Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective
Open accessThe DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
Two interlocking research questions of growing interest and importance in privacy research are Authorship Attribution (AA) and Authorship Obfuscation (AO). Given an artifact, especially a text t in question, an AA solution aims to accurately attribute t to its true author out of many candidate authors while an AO solution aims to modify t to hide its true authorship. Traditionally, the notion of authorship and its accompanying privacy concern is only toward human authors. However, in recent years, due to the explosive advancements in Neural Text Generation (NTG) techniques in NLP, capable of synthesizing human-quality openended texts (so-called "neural texts"), one has to now consider authorships by humans, machines, or their combination. Due to the implications and potential threats of neural texts when used maliciously, it has become critical to understand the limitations of traditional AA/AO solutions and develop novel AA/AO solutions in dealing with neural texts. In this survey, therefore, we make a comprehensive review of recent literature on the attribution and obfuscation of neural text authorship from a Data Mining perspective, and share our view on their limitations and promising research directions.
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
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
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Transformer-XL: Attentive language models beyond a fixed-length context
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1285 · Cited by 3,169 · cited 1×
“TRANSFORMER_XL [24] Google Another Transformer model that learns long-term dependency to improve long coherent text generation PPLM [25] Uber The Plug and Play Language Models (PPLM) model upon GPT-2 by fusing the GPT-2 medium with a bag of words (BoW) models.”
MethodChatting and cheating: Ensuring academic integrity in the era of ChatGPT
Cotton, D. R. E., Cotton, P. A., & Shipway, J. R. (2024) · Innovations in Education and Teaching International · doi:10.1080/14703297.2023.2190148 · Cited by 3,087
Chatting and Cheating. Ensuring academic integrity in the era of ChatGPT
Cotton, D., Cotton, P., & Shipway, J. R. (2023) · doi:10.35542/osf.io/mrz8h · Cited by 3,079
SimCSE: Simple Contrastive Learning of Sentence Embeddings
Gao, T., Yao, X., & Chen, D. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.552 · Cited by 2,851
Universal Sentence Encoder for English
Cer, D., Yang, Y., Kong, S.-Y., Hua, N., Limtiaco, N., St. John, R., Constant, N., Guajardo-Cespedes, M., Yuan, S., Tar, C., et al. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/d18-2029 · Cited by 1,750
Cross-lingual Language Model Pretraining
Lample, G., & Conneau, A. (2019) · arXiv · doi:10.48550/arxiv.1901.07291 · Cited by 1,586 · cited 2×
“There are 3 pre-trained models: GROVER-base , GROVER-large , GROVER-mega CTRL [59] Salesforce Conditional Transformer LM For controllable generation uses control codes to guide generation XLM [20] Facebook A Cross-lingual Language Model trained on various languages.”
BackgroundThe Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304
Hierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1082 · Cited by 1,266 · cited 1×
“The following 3 datasets are perturbed - human-machine pairs, Writing Prompt dataset [33], and CnDARIO (Chinese Novel Dataset crAwled fRom mIxed online sOurces) generated with GPT-2 finetuned with Chinese Literature.”
MethodHierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.04833 · Cited by 1,242
Gao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2022) · doi:10.1101/2022.12.23.521610 · Cited by 1,099
Online Human-Bot Interactions: Detection, Estimation, and Characterization
Varol, O., Ferrara, E., Davis, C., Menczer, F., & Flammini, A. (2017) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v11i1.14871 · Cited by 981
The Creation and Detection of Deepfakes: A Survey
Mirsky, Y., & Lee, W. (2020) · arXiv · doi:10.48550/arxiv.2004.11138 · Cited by 863
The Creation and Detection of Deepfakes: A Survey
Mirsky, Y., & Lee, W. (2022) · ACM Computing Surveys · doi:10.1145/3425780 · Cited by 863 · cited 1×
“While most of these deepfakes are made for humor, some are malicious in generating misinformation, spreading political propaganda, or attacking individuals [79].”
BackgroundCTRL: A Conditional Transformer Language Model for Controllable Generation
Keskar, N. S., McCann, B., Varshney, L. R., Xiong, C., & Socher, R. (2019) · arXiv · doi:10.48550/arxiv.1909.05858 · Cited by 751
Black-Box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
Gao, J., Lanchantin, J., Soffa, M. L., & Qi, Y. (2018) · 2018 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2018.00016 · Cited by 693
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Gehman, S., Gururangan, S., Sap, M., Choi, Y., & Smith, N. A. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.301 · Cited by 693
ChatGPT and the future of medical writing
Biswas, S. (2023) · Radiology · doi:10.1148/radiol.223312 · Cited by 571
Defending Against Neural Fake News
Zellers, R., Holtzman, A., Rashkin, H., Bisk, Y., Farhadi, A., Roesner, F., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1905.12616 · Cited by 569 · cited 11×
“When used maliciously, therefore, such a text generation capability can be misused to generate misinformation [12, 99], online shopping fake reviews [2] and propaganda [92] at scale with little cost.”
BackgroundMethodInfluentialPlug and Play Language Models: A Simple Approach to Controlled Text Generation
Dathathri, S., Madotto, A., Lan, J., Hung, J., Frank, E., Molino, P., Yosinski, J., & Liu, R. (2019) · arXiv · doi:10.48550/arxiv.1912.02164 · Cited by 508
GLTR: Statistical Detection and Visualization of Generated Text
Gehrmann, S., Strobelt, H., & Rush, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/p19-3019 · Cited by 470 · cited 6×
“The first statistical AA classifier proposed for NTD is GLTR [45].”
BackgroundMethodInfluentialGLTR: Statistical Detection and Visualization of Generated Text
Gehrmann, S., Strobelt, H., & Rush, A. M. (2019) · arXiv · doi:10.48550/arxiv.1906.04043 · Cited by 460
Empath: Understanding Topic Signals in Large-Scale Text
Fast, E., Chen, B., & Bernstein, M. S. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858535 · Cited by 413
All the News That’s Fit to Fabricate: AI-Generated Text as a Tool of Media Misinformation
Kreps, S., McCain, R. M., & Brundage, M. (2022) · Journal of Experimental Political Science · doi:10.1017/xps.2020.37 · Cited by 360 · cited 1×
“…2 https://huggingface.co/models?pipeline_tag= text-generation 3 Other names for neural text include AI(-generated) text [66], Machine(-generated/written) text [1, 5, 36, 38, 45, 89, 96, 104, 107, 108, 117], Artificial text [67], Computer-generated text [102], Deepfake…”
BackgroundAll That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text
Clark, E., August, T., Serrano, S., Haduong, N., Gururangan, S., & Smith, N. A. (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.565 · Cited by 290 · cited 8×
“These datasets are in 3 different domains, respectively - Online Forum, News, and Literature.”
BackgroundMethodInfluentialAll That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text
Clark, E., August, T., Serrano, S., Haduong, N., Gururangan, S., & Smith, N. A. (2021) · arXiv · doi:10.48550/arxiv.2107.00061 · Cited by 290
Automatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2019) · arXiv · doi:10.48550/arxiv.1911.00650 · Cited by 264 · cited 7×
“[44] evaluated the quality of top-p and top-k decoding strategies, and found that (1) AA models detect neural”
BackgroundMethodInfluentialAutomatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.164 · Cited by 264 · cited 7×
“[44] evaluated the quality of top-p and top-k decoding strategies, and found that (1) AA models detect neural”
BackgroundMethodInfluentialGeDi: Generative Discriminator Guided Sequence Generation
Krause, B., Gotmare, A. D., McCann, B., Keskar, N. S., Joty, S., Socher, R., & Rajani, N. F. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.424 · Cited by 220
TweepFake: about detecting deepfake tweets
Fagni, T., Falchi, F., Gambini, M., Martella, A., & Tesconi, M. (2021) · PLOS ONE · doi:10.1371/journal.pone.0251415 · Cited by 185 · cited 1×
“TweepFake [32] Collected tweets generated by Twitter bots and grouped them into tweets generated by GPT-2, RNN, and other bots Binary Tweets Human & Machine”
MethodDetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
Mitchell, E., Lee, Y., Khazatsky, A., Manning, C. D., & Finn, C. (2023) · arXiv · doi:10.48550/arxiv.2301.11305 · Cited by 151
Good News, Everyone! Context Driven Entity-Aware Captioning for News Images
Biten, A. F., Gomez, L., Rusiñol, M., & Karatzas, D. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01275 · Cited by 136 · cited 1×
“UsingtheGoodNews[11]datasetasthe human-writtenprompttogeneratetextswith GROVER.”
The limitations of stylometry for detecting machine-generated fake news
Schuster, T., Schuster, R., Shah, D. J., & Barzilay, R. (2020) · Computational Linguistics · doi:10.1162/coli_a_00380 · Cited by 109
Feature-based detection of automated language models: tackling GPT-2, GPT-3 and Grover
Fröhling, L., & Zubiaga, A. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.443 · Cited by 106
TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation
Uchendu, A., Ma, Z., Le, T., Zhang, R., & Lee, D. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.172 · Cited by 82
Self-citationDetecting computer-generated disinformation
Stiff, H., & Johansson, F. (2022) · International Journal of Data Science and Analytics · doi:10.1007/s41060-021-00299-5 · Cited by 79 · cited 8×
“In addition, the Authorship Attribution-AA dataset is included in this in-the-wild test set [85].”
BackgroundMethodInfluentialReal or Fake? Learning to Discriminate Machine from Human Generated Text
Bakhtin, A., Gross, S., Ott, M., Deng, Y., Ranzato, M., & Szlam, A. (2019) · arXiv · doi:10.48550/arxiv.1906.03351 · Cited by 77
A Survey on Stylometric Text Features
Lagutina, K., Lagutina, N., Boychuk, E., Vorontsova, I., Shliakhtina, E., Belyaeva, O., Paramonov, I., & Demidov, P. G. (2019) · 2019 25th Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct48121.2019.8981504 · Cited by 63 · cited 1×
“This has been shown to be a successful approach for traditional AA tasks [68].”
BackgroundIdentifying computer-generated text using statistical analysis
Nguyen-Son, H.-Q., Tieu, N.-D. T., Nguyen, H. H., Yamagishi, J., & Zen, I. E. (2017) · 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2017.8282270 · Cited by 30
On pushing DeepFake Tweet Detection capabilities to the limits
Gambini, M., Fagni, T., Falchi, F., & Tesconi, M. (2022) · 14th ACM Web Science Conference 2022 · doi:10.1145/3501247.3531560 · Cited by 19 · cited 3×
“Finally, using an Ensemble classifier (BART, BERTweet, and TwitterRoberta), [39] achieves an 84% accuracy in distinguishing between GPT-2 and human tweets.”
MethodAttacking Neural Text Detectors
Wolff, M., & Wolff, S. (2020) · arXiv · doi:10.48550/arxiv.2002.11768 · Cited by 18
How effectively can machines defend against machine-generated fake news? An empirical study
Bhat, M. M., & Parthasarathy, S. (2020) · Proceedings of the First Workshop on Insights from Negative Results in NLP · doi:10.18653/v1/2020.insights-1.7 · Cited by 16 · cited 9×
“Entity replacement [9] Black-box Stylometric (Lexical) ✓ GROVER”
BackgroundMethodInfluentialThrough the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models
Munir, S., Batool, B., Shafiq, Z., Srinivasan, P., & Zaffar, F. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.155 · Cited by 11 · cited 7×
“3Other names for neural text include AI(-generated) text [51], Machine(generated/written) text [1, 5, 30, 32, 37, 71, 79, 87, 90, 91, 99], Artificial text [52], Computer-generated text [85], Deepfake text [73], Auto-generated text [67], and and Synthetic text [12, 23, 64].”
BackgroundMethodInfluential
Cited by
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
Wu, J., Yang, S., Zhan, R., Yuan, Y., Wong, D. F., & Chao, L. S. (2023) · arXiv · doi:10.48550/arxiv.2310.14724 · Cited by 212
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
Wu, J., Yang, S., Zhan, R., Yuan, Y., Chao, L. S., & Wong, D. F. (2025) · Computational Linguistics · doi:10.1162/coli_a_00549 · Cited by 212
Combating misinformation in the age of LLMs: Opportunities and challenges
Chen, C., & Shu, K. (2024) · AI Magazine · doi:10.1002/aaai.12188 · Cited by 148
Srba, I., Razuvayevskaya, O., Leite, J. A., Moro, R., Schlicht, I. B., Tonelli, S., García, F. M., Lottmann, S. B., Teyssou, D., Porcellini, V., et al. (2026) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3770077 · Cited by 19
HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis
Tripto, N., Uchendu, A., Le, T., Setzu, M., Giannotti, F., & Lee, D. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.916 · Cited by 6
Self-citation
Metadata
- Authors
- Uchendu, A., Le, T., & Lee, D.
- Venue
- ACM SIGKDD Explorations Newsletter
- Published
- 2023-06-22
- Volume
- 25
- Issue
- 1
- Pages
- 1-18
- ISSN
- 1931-0145 (ISSN-L)
- 1931-0153
- OpenAlex
- W4383199647
- Cited by
- 31
- References
- 46
- FWCI
- 2.72
- Type
- journal article
- Language
- en
- Open access
- bronze
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.