How effectively can machines defend against machine-generated fake news? An empirical study
Open accessAbstract
We empirically study the effectiveness of machine-generated fake news detectors by understanding the model's sensitivity to different synthetic perturbations during test time.The current machine-generated fake news detectors rely on provenance to determine the veracity of news.Our experiments find that the success of these detectors can be limited since they are rarely sensitive to semantic perturbations and are very sensitive to syntactic perturbations.Also, we would like to open-source our code and believe it could be a useful diagnostic tool for evaluating models aimed at fighting machine-generated fake news.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Detectors are more sensitive to syntactic perturbations, including breaking longer sentences, removing definite articles, semantic-preserving rule conversions, and reformatting paragraphs of machine-generated text.
“Moreover, Bhat and Parthasarathy (2020) showed that detectors are more sensitive to syntactic perturbations, including breaking longer sentences, removing definite articles, using semantic-preserving rule conversions (such as changing 'that's' to 'that is'), and reformatting paragraphs of machine-generated text.”
From A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions (2025) · cites this paper as Bhat and Parthasarathy (2020)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 26 · Cited by 16
Research works printed but not linked: 18
- Isabelle Augenstein, Christina Lioma, Dongsheng Wang, Lucas Chaves Lima, Casper Hansen, Chris- tian Hansen, and Jakob Grue Simonsen. 2019. Mul- tifc: A real-world multi-domain dataset for evidence- based fact checking of claims. Proceedings of the 2019 Conference on Empirical Methods in Natu- ral Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). · DOI
- Anton Bakhtin, Sam Gross, Myle Ott, Yuntian Deng, Marc'Aurelio Ranzato, and Arthur Szlam. 2019. Real or fake? learning to discriminate machine from human generated text. CoRR, abs/1906.03351. · arXiv
- M. Behjati, S. Moosavi-Dezfooli, M. S. Baghshah, and P. Frossard. 2019. Universal adversarial attacks on text classifiers. In ICASSP 2019 -2019 IEEE Inter- national Conference on Acoustics, Speech and Sig- nal Processing (ICASSP), pages 7345-7349.
- Nina Mazar, On Amir, and Dan Ariely. 2008. The dishonesty of honest people: A theory of self- concept maintenance. Journal of Marketing Re- search, 45(6):633-644. · DOI · Paper page
- Ramesh Nallapati, Bing Xiang, and Bowen Zhou. 2016. Sequence-to-sequence rnns for text summarization. CoRR, abs/1602.06023. · arXiv
- Yixin Nie, Haonan Chen, and Mohit Bansal. 2018. Combining fact extraction and verification with neural semantic matching networks. CoRR, abs/1811.07039. · arXiv
- Kashyap Popat, Subhabrata Mukherjee, Andrew Yates, and Gerhard Weikum. 2018. Declare: Debunking fake news and false claims using evidence-aware deep learning. CoRR, abs/1809.06416. · arXiv
- Hannah Rashkin, Eunsol Choi, Jin Yea Jang, Svitlana Volkova, and Yejin Choi. 2017. Truth of varying shades: Analyzing language in fake news and polit- ical fact-checking. In Proceedings of the 2017 Con- ference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017, pages 2931-2937. Associa- tion for Computational Linguistics. · DOI
- Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Semantically equivalent adversar- ial rules for debugging NLP models. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 856-865, Melbourne, Australia. Association for Computational Linguistics. · DOI
- Chinnadhurai Sankar, Sandeep Subramanian, Christo- pher J. Pal, Sarath Chandar, and Yoshua Bengio. 2019. Do neural dialog systems use the conversa- tion history effectively? an empirical study. CoRR, abs/1906.01603. · arXiv
- Tal Schuster, Roei Schuster, Darsh J Shah, and Regina Barzilay. 2019. Are we safe yet? the limitations of distributional features for fake news detection. arXiv preprint arXiv:1908.09805. · arXiv
- Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get to the point: Summarization with pointer- generator networks. In Proceedings of the 55th An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1073- 1083, Vancouver, Canada. Association for Computa- tional Linguistics. · DOI · Paper page
- Kai Shu, Amy Sliva, Suhang Wang, Jiliang Tang, and Huan Liu. 2017. Fake news detection on social me- dia: A data mining perspective. SIGKDD Explor. Newsl., 19(1):22-36. · DOI · Paper page
- James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. In NAACL-HLT.
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NIPS.
- William Yang Wang. 2017. "liar, liar pants on fire": A new benchmark dataset for fake news detection. ArXiv, abs/1705.00648. · arXiv
- Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi. 2019. Defending against neural fake news. In Advances in Neural Information Process- ing Systems 32: Annual Conference on Neural Infor- mation Processing Systems 2019, NeurIPS 2019, 8- 14 December 2019, Vancouver, BC, Canada, pages 9051-9062.
- Zhixuan Zhou, Huankang Guan, Meghana Moorthy Bhat, and Justin Hsu. 2019. Fake news detection via NLP is vulnerable to adversarial attacks. CoRR, abs/1901.09657. · arXiv
- Authors
- Bhat, M. M., & Parthasarathy, S.
- Affiliations
- The Ohio State University (US)
- Venue
- Proceedings of the First Workshop on Insights from Negative Results in NLP
- Published
- 2020
- Pages
- 48-53
- OpenAlex
- W3106359033
- Cited by
- 16
- References
- 26
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 3 · 2023: 3 · 2022: 1 · 2021: 2 · 2020: 1
- FWCI
- 3.71
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Workshop on Insights from Negative Results in NLP (Insights) (publishedVersion, cc-by)
- Funders
- National Science Foundation (1520870)
- Topics
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- fake news detection, adversarial perturbations, semantic perturbation, provenance, model robustness, adversarial robustness
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
