49 citations · 125 across the 16 of their papers we have counts for
4 papers · 1 filter
UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning
Ziyao Wang, Thai Le, Dongwon Lee
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 attr…
Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective
Adaku Uchendu, Thai Le, Dongwon Lee
Two interlocking research questions of growing interest and importance in privacy research are Authorship Attribution (AA) and Authorship Obfuscation (AO). Given an artifact, espec…
Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense
Thai Le, Jooyoung Lee, Kevin Yen +2
We proposes a novel algorithm, ANTHRO, that inductively extracts over 600K human-written text perturbations in the wild and leverages them for realistic adversarial attack. Unlike…
Do Language Models Plagiarize?
Jooyoung Lee, Thai Le, Jinghui Chen +1
Past literature has illustrated that language models (LMs) often memorize parts of training instances and reproduce them in natural language generation (NLG) processes. However, it…