UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning

Ziyao Wang, Thai Le, Dongwon Lee


Abstract
Consider a scenario where an author (e.g., activist, whistle-blower) with many public writings wishes to write “anonymously” when attackers may have already built an authorship attribution (AA) model based off of public writings including those of the author. To enable her wish, we ask a question “can one make the publicly released writings, T , unattributable so that AA models trained on T cannot attribute its authorship well?” Toward this question, we present a novel solution, UPTON, that exploits black-box data poisoning methods to weaken the authorship features in training samples and make released texts unlearnable. It is different from previous obfuscation works (e.g., adversarial attacks that modify test samples or backdoor works that only change the model outputs when triggering words occur). Using four authorship datasets (IMDb10, IMDb64, Enron and WJO), we present empirical validation where UPTON successfully downgrades the accuracy of AA models to the impractical level (e.g., ~ 35%) while keeping texts still readable (e.g., > 0.9 in BERTScore). UPTON remains effective to AA models that are already trained on available clean writings of authors.
Anthology ID:
2023.findings-emnlp.800
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11952–11965
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.800
DOI:
10.18653/v1/2023.findings-emnlp.800
Bibkey:
Cite (ACL):
Ziyao Wang, Thai Le, and Dongwon Lee. 2023. UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 11952–11965, Singapore. Association for Computational Linguistics.
Cite (Informal):
UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning (Wang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.800.pdf