# A Girl Has A Name: Detecting Authorship Obfuscation

arXiv: https://arxiv.org/abs/2005.00702 · HTML: https://mlsanity.com/paper/2005.00702/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2020.

## Built on by (most cited first, 7 of 7)

- [Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective](https://mlsanity.com/paper/2210.10488/) (2022)
- [Who Wrote it and Why? Prompting Large-Language Models for Authorship Verification](https://mlsanity.com/paper/2310.08123/) (2023)
- [Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators](https://mlsanity.com/paper/2203.09813/) (2022)
- [Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling](https://mlsanity.com/paper/2101.11310/) (2021)
- [JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models](https://mlsanity.com/paper/2402.08761/) (2024)
- [A Girl Has A Name, And It's ... Adversarial Authorship Attribution for Deobfuscation](https://mlsanity.com/paper/2203.11849/) (2022)
- [Large Language Models Threaten Double-blind Review](https://mlsanity.com/paper/2608.05157/) (2026)

## Abstract (arXiv)

Authorship attribution aims to identify the author of a text based on the stylometric analysis. Authorship obfuscation, on the other hand, aims to protect against authorship attribution by modifying a text's style. In this paper, we evaluate the stealthiness of state-of-the-art authorship obfuscation methods under an adversarial threat model. An obfuscator is stealthy to the extent an adversary finds it challenging to detect whether or not a text modified by the obfuscator is obfuscated - a decision that is key to the adversary interested in authorship attribution. We show that the existing authorship obfuscation methods are not stealthy as their obfuscated texts can be identified with an average F1 score of 0.87. The reason for the lack of stealthiness is that these obfuscators degrade text smoothness, as ascertained by neural language models, in a detectable manner. Our results highlight the need to develop stealthy authorship obfuscation methods that can better protect the identity of an author seeking anonymity.