Papers with Authorship obfuscation techniques

2 papers
A Multifaceted Framework to Evaluate Evasion, Content Preservation, and Misattribution in Authorship Obfuscation Techniques (2022.emnlp-main)

Copied to clipboard

Challenge: Authorship obfuscation techniques are often evaluated based on their ability to hide the author’s identity (evasion) while preserving the content of the original text.
Approach: They propose to evaluate authorship obfuscation techniques on detection evasion and content preservation using competitive identification techniques in real-life scenarios.
Outcome: The proposed method reveals key weaknesses in state-of-the-art obfuscation techniques and surprisingly competitive effectiveness from a back-translation baseline in all evaluation aspects.
Keep it Private: Unsupervised Privatization of Online Text (2024.naacl-long)

Copied to clipboard

Challenge: Authorship obfuscation has been evaluated in narrow settings in the NLP literature . superficial edit operations can lead to unnatural outputs, authors say .
Approach: They propose an automatic text privatization framework that fine-tunes a large language model via reinforcement learning to produce rewrites that balance soundness, sense, and privacy.
Outcome: The proposed method maintains high text quality according to automated metrics and human evaluation, and successfully evades several automated authorship attacks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations