no code implementations • 15 Sep 2021 • Muhammad Haroon, Fareed Zaffar, Padmini Srinivasan, Zubair Shafiq
Our experiments show that if an obfuscator can evade an ensemble attribution classifier, which is based on multiple base attribution classifiers, it is more likely to transfer to different attribution classifiers.
no code implementations • EACL 2021 • Shaoor Munir, Brishna Batool, Zubair Shafiq, Padmini Srinivasan, Fareed Zaffar
Given the potential misuse of recent advances in synthetic text generation by language models (LMs), it is important to have the capacity to attribute authorship of synthetic text.