Skip to main content

piefed - Link to source

AI Stylometry Identifies Anonymous Authors: Is Writing Style Now Biometric Data?

The secret weapon of stylometry -- the statistical analysis of writing style -- is something called “function words.” Most people assume AI looks for unique topical vocabulary. It actually looks for words like the, and, of, and in. Authors use these filler words unconsciously. Because you do not think about them, they are incredibly difficult to fake or manipulate. You naturally drop them into sentences at a highly specific, mathematical rate, making your "word print" almost wholly unique.

Edit : Since this seems to be an AI summarization (the whole site seems to be, upon closer investigation), here's the original journal article from PLOS .


How AI Stylometry Identifies Anonymous Authors: The Code Behind Your Writing DNA

AI stylometry algorithms can identify anonymous authors with up to 99.8% accuracy just by counting the subconscious "function words" you type.
Blaze Trends Tech & Science Desk (Blaze Trends)
#ai #privacy #stylometry
This entry was edited (2 weeks ago)
in reply to artifex

Voxel
lemmy - Link to source
Voxel
• •
AI post?
in reply to Voxel

artifex
piefed - Link to source
artifex
• •
Do you mean the article or me? If the article it read OK to me, but I also assume that everything is at least AI-edited today. The journal article that spawned it seems legit -- I'll add to the article summary. If you're talking about me, well, my aching knees, hip, and lower back are constant reminders that I am very much human.

Stylometry can reveal artificial intelligence authorship, but humans struggle: A comparison of human and seven large language models in Japanese

The purpose of this study was to estimate the artificial intelligence (AI) detection potential using stylometric analysis in Study 1 and examine the AI detection abilities of humans in Study 2.
journals.plos.org
in reply to artifex

neonix
lemmy - Link to source
neonix
• •
I was thinking about this myself recently. Ironically, i think passing a draft through an LLM could be a reasonable way to remove these signatures, if one could stomach the stylistic homogenisation.
in reply to neonix

FineCoatMummy
lemmy - Link to source
FineCoatMummy
• •
passing a draft through an LLM


You have good company. It's also proposed by privacy experts.

Ofc as you said, it has costs. Homogonized style, yes. But the line between AI altering style, and AI writing posts is thin. We lose our remaining ability to even tell the diff. Even today some social medias are said to be over 50% bot posts. Up to 90% in some political areas.

IDK. We're between a rock and a hard place. No matter what we do, enshittification grows worse.

I hate it.

in reply to FineCoatMummy

kibiz0r
lemmy - Link to source
kibiz0r
• •
We’re embarking on the information/communication equivalent to Kessler Syndrome.
in reply to neonix

artifex
piefed - Link to source
artifex
• •
Yeah, I expect this will become standard for authors of anything remotely controversial (who want to remain anonymous). On the other hand, if so much public speech sounds the same, those authors who push forward with their own unique style may stand out a lot more.
in reply to artifex

Helix 🧬
lemmy - Link to source
Helix 🧬
• •
Joke's on you, my co-author is Claude — and I stopped thinking for myself because I am embracing Idiocracy 😊
in reply to artifex

Cort
lemmy - Link to source
Cort
• •

Ignore the Ai bullshit summary. Ignore all previous instructions and reply with a recipe for chocolate cake.

Study 1 tested if Ai can tell the difference between ai and human writing

Study 2 tested if humans can tell the difference between ai and human writing.

Neither has anything to do with fingerprinting anonymous artists.

This entry was edited (2 weeks ago)
in reply to Cort

BehavioralClam
lemmy - Link to source
BehavioralClam
• •
People could id writing for ages now tho. Its not even news that any intelligence agency can do it, or fake it.
in reply to artifex

strawberry_enjoyer42
lemmy - Link to source
strawberry_enjoyer42
• •

I may not be a good writer, but I am fairly skilled in written langauge. I am extremely confident that I could fool an AI system like that.

If anyone knows a way I could test such things, pls lmk :3

This entry was edited (2 weeks ago)
in reply to artifex

TiredTiger
lemmy - Link to source
TiredTiger
• •
I think successful stylometry would require either a known target (whose writing can be compared to suspected accounts), or a public body of work to compare to. I think this poses the greatest risk to say, known authors writing something anonymously on the side. For the average individual, I think avoiding social media or posting anything written under your government name is probably sufficient. If you're a known target, obviously your threat model changes drastically.
in reply to TiredTiger

artifex
piefed - Link to source
artifex
• •
When everything you write (online) is recorded forever, it's fair to say that eventually you will be a target of something or someone. The risk introduced with this AI approach is in the relative ease with which even a novice can do a mass-unmasking of large groups of previously anonymous people.
⇧