fmaury/seirdy.one
1
0
Fork 0
mirror of https://git.sr.ht/~seirdy/seirdy.one synced 2024-09-19 20:02:10 +00:00
Code Issues Projects Releases Wiki Activity

Typo

Browse source
This commit is contained in:
Rohan Kumar 2022-06-24 16:27:36 -07:00
parent 251236d0da
commit 8bba9dd511
No known key found for this signature in database
GPG key ID: 1E892DB2A5F84479
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
content/notes/stylometric-fingerprinting-resistance.md
View file

@ -10,7 +10,7 @@ Few guides cover [stylometric fingerprinting.](https://en.wikipedia.org/wiki/Sty
Common advice is to use offline machine translation to translate works to and from another language. [Argos Translate](https://www.argosopentech.com/) and [Marian](https://marian-nmt.github.io/) are two options that come to mind.
{{<mention-work itemprop="citation" role="doc-crdit" itemtype="ScholarlyArticle">}}{{<cited-work name="Adversarial stylometry: Circumventing authorship recognition to preserve privacy and anonymity" extraName="headline" url="https://doi.org/10.1145/2382448.2382450">}}{{</mention-work>}} shows that machine translation alone isn't nearly as strong a method as manual approaches: obfuscation (hiding your writing style) or imitation (mimicking another author). These approaches have excellent success rates, even among amateur writers. The aforementioned Whonix wiki page lists common stylometric fingerprinting vectors for manual approaches to address.
{{<mention-work itemprop="citation" role="doc-credit" itemtype="ScholarlyArticle">}}{{<cited-work name="Adversarial stylometry: Circumventing authorship recognition to preserve privacy and anonymity" extraName="headline" url="https://doi.org/10.1145/2382448.2382450">}}{{</mention-work>}} shows that machine translation alone isn't nearly as strong a method as manual approaches: obfuscation (hiding your writing style) or imitation (mimicking another author). These approaches have excellent success rates, even among amateur writers. The aforementioned Whonix wiki page lists common stylometric fingerprinting vectors for manual approaches to address.
Limiting unusual vocabulary and sentence structure make for a good start. Using a comprehensive and highly-opinionated style-guide should also help. <cite>The Economist</cite> has a good one that was specifically written to make all authors sound the same: {{<mention-work itemtype="Book">}}{{<cited-work name="The Economist Style Guide" url="http://cdn.static-economist.com/sites/default/files/pdfs/style_guide_12.pdf">}}, <span itemprop="bookEdition">12th edition</span> (<span itemprop="encodingFormat">application/<wbr />pdf</span>){{</mention-work>}}.