Conversation

Notices

Embed this notice
CyberFrog (froge@social.glitched.systems)'s status on Wednesday, 29-Jan-2025 05:45:18 JST CyberFrog

Reminder for those who may not realize this, but #Stylometry is kind of an insane field of study, and you can be uniquely identified based on your writing style alone.

This has, in the past, been applied to open source developers and programming code too, and it was found that using stylometry techniques you can identify the author of a compiled binary based on their open source code style ~78% of the time

https://arxiv.org/pdf/1512.08546v1

There are some techniques to avoid this luckily, which involve fairly basic changes to your writing style and structure that can very effectively anonymize things again:

https://en.wikipedia.org/wiki/Adversarial_stylometry
In conversation about 3 months ago from social.glitched.systems permalink
Attachments
1. Untitled attachment
2. No result found on File_thumbnail lookup.
  
  Adversarial stylometry
  
  Adversarial stylometry is the practice of altering writing style to reduce the potential for stylometry to discover the author's identity or their characteristics. This task is also known as authorship obfuscation or authorship anonymisation. Stylometry poses a significant privacy challenge in its ability to unmask anonymous authors or to link pseudonyms to an author's other identities, which, for example, creates difficulties for whistleblowers, activists, and hoaxers and fraudsters. The privacy risk is expected to grow as machine learning techniques and text corpora develop. All adversarial stylometry shares the core idea of faithfully paraphrasing the source text so that the meaning is unchanged but the stylistic signals are obscured. Such a faithful paraphrase is an adversarial example for a stylometric classifier. Several broad approaches to this exist, with some overlap: imitation, substituting the author's own style for another's; translation, applying machine translation with the hope that this eliminates characteristic style in the source text; and obfuscation, deliberately modifying a text's...

Public

Conversation

Notices

Feeds