SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.11849 · ACL · 2022

A Girl Has A Name, And It's ... * Adversarial Authorship Attribution for Deobfuscation †

Zubair Shafiq, Jonathan Rusert, Padmini Srinivasan, Wanyue Zhai

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent advances in natural language processing have enabled powerful privacy-invasive authorship attribution. To counter authorship attribution, researchers have proposed a variety of rule-based and learning-based text obfuscation approaches. However, existing authorship obfuscation approaches do not consider the adversarial threat model. Specifically, they are not evaluated against adversarially trained authorship attributors that are aware of potential obfuscation. To fill this gap, we investigate the problem of adversarial authorship attribution for deobfuscation. We show that adversarially trained authorship attributors are able to degrade the effectiveness of existing obfuscators from 20-30% to 5-10%. We also evaluate the effectiveness of adversarial training when the attributor makes incorrect assumptions about whether and which obfuscator was used. While there is a a clear degradation in attribution accuracy, it is noteworthy that this degradation is still at or above the attribution accuracy of the attributor that is not adversarially trained at all. Our results underline the need for stronger obfuscation approaches that are resistant to deobfuscation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.11849")
get_code_for_paper("2203.11849")
have("2203.11849")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.11849.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.11849.svg)](https://syntology.ai/paper/2203.11849)

Connect an agent — have() is free.