Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective
Adaku Uchendu, Thai Le, Dongwon Lee
ArXiV. October 2022 (Under Review)
Tutorial on Artificial Text Detection
Adaku Uchendu, Vladislav Mikhailov, Jooyoung Lee, Saranya Venkatraman, Tatiana Shavrina, Ekaterina Artemova
The 15th International Conference on Natural Language Generation (INLG). Maine, July 2022 (Tutorial) [Video]
- Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks
Adaku Uchendu, Daniel Campoy, Christopher Menart, Alexandra Hildenbrandt
IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE). IEEE, 2021.
TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation
Adaku Uchendu, Zeyu Ma, Thai Le, Rui Zhang, Dongwon Lee
In Findings of the Association for Computational Linguistics: EMNLP 2021. (Acceptance Rate: 11.6% (419/3,600))
Authorship Attribution for Neural Text Generation
Adaku Uchendu, Thai Le, Kai Shu, Dongwon Lee.
In Conf. on Empirical Methods in Natural Language Processing (EMNLP), Virtual Event, November 2020. (Acceptance Rate: 22.4% (754/3,359))
Characterizing Man-made vs. Machine-made Chatbot Dialogs
Adaku Uchendu, Jeffrey Cao, Qiaozhi Wang, Bo Luo, Dongwon Lee.
In Conf. on Truth and Trust Online (TTO), London, UK, October 2019.
- A Reverse Turing Test for Detecting Machine-Made Texts
Jialin Shao, Adaku Uchendu, Dongwon Lee. (2019).
In 11th Int’l ACM Web Science Conf. (WebSci), Boston, MA, July 2019.
Detection and Obfuscation of Deepfake Texts, at MIT Lincoln Laboratory’s fourth Recent Advances in Artificial Intelligence for National Security (RAAINS) workshop, Student Lightning talk, Boston, MA, November 16, 2022.
Attribution and Obfuscation of Neural Text Authorship, at Dublin City University, Ireland, NLP Seminar, Virtual, October 10, 2022
Reverse Turing Test in the Age of Neural Text Generation, at National Institute of Standards and Technology (NIST), Information Technology Laboratory, Software and Systems Division, Virtual, February 10, 2022.
Reverse Turing Tests for Distinguishing AI-generated texts from Human-written texts, at National Institute of Standards and Technology (NIST), Applied and Computational Mathematics Division (ACMD) Seminar Series, Virtual, May 25, 2021.