Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

US Government plans to develop AI that can unmask anonymous writers

reclaimthenet.org

Post reply on HN
Print view View original

81–90 of 219 posts

Re: US Government plans to develop AI that can unmask anonymous writers

#81

Post by kps »

dehrmann wrote: post #8

Plans? I assumed lots of people were already working on this. There's already a lot of training data out there, and I suspect most users can be identified by use of a handful of uncommon trigrams and sentence stats. I know you can recognize things I've written at work because they have real em dashes—people rarely type with those.

I use em dashes — though with space — and also ellipses… Also 2×4s (that are actually 1½×3½), where 2 ≠ 4 above −270°C, and footnotes¹ and all that.

¹ There.

Re: US Government plans to develop AI that can unmask anonymous writers

#82

Post by dehrmann »

_8j50 wrote: post #10
dehrmann wrote: post #8

Plans? I assumed lots of people were already working on this. There's already a lot of training data out there, and I suspect most users can be identified by use of a handful of uncommon trigrams and sentence stats. I know you can recognize things I've written at work because they have real em dashes—people rarely type with those.

NSA already does this. "Stylometry" I believe is the term. Perhaps they used heuristics and algorithms so far? I would NLP was good enough for this years ago.

Back in 2015 you might have some linguists work with data scientists to do feature engineering and use those as inputs to an LR model. I suppose you can let a deep learning model feature engineer for you, but either way, you'll get to some of the same heuristics you're thinking of.

Re: US Government plans to develop AI that can unmask anonymous writers

#83

Post by ravenstine »

vmoore wrote: post #48
MonkeyMalarky wrote: post #24

Earlier quoted context omitted.

Someone unintentionally did something similar with HN comments to find users who sound most similar to you/eachother and people were finding their throwaway and alt accounts.

Yes I recall that: 'Find Your Hacker News Doppelgänger': https://news.ycombinator.com/item?id=27568709

Neat experiment, though it took me fewer than 30 seconds to rule out my nearest "doppelganger". Too many patterns there I've never used.

Re: US Government plans to develop AI that can unmask anonymous writers

#84

Post by notadev »

lajamerr wrote: post #36
dehrmann wrote: post #8

Plans? I assumed lots of people were already working on this. There's already a lot of training data out there, and I suspect most users can be identified by use of a handful of uncommon trigrams and sentence stats. I know you can recognize things I've written at work because they have real em dashes—people rarely type with those.

The next step after is to build an AI to convert your style of writing to another person's style.

Running all writing through AI to re-write everything in a different style while conveying the same information might work. Create a way to apply it to all online writing and you have something like a writing VPN.

Re: US Government plans to develop AI that can unmask anonymous writers

#85

Post by klabb3 »

lajamerr wrote: post #36
dehrmann wrote: post #8

Plans? I assumed lots of people were already working on this. There's already a lot of training data out there, and I suspect most users can be identified by use of a handful of uncommon trigrams and sentence stats. I know you can recognize things I've written at work because they have real em dashes—people rarely type with those.

The next step after is to build an AI to convert your style of writing to another person's style.

Exactly. You barely need "AI" for this. Changing style enough to put some sand in a sophisticated text identifier could be as simple as introducing some spelling and grammar variations. It could easily be commoditized (isn't grammarly doing this already minus the privacy part?). Of all cat and mouse games LE and intelligence are playing, for this one I'm betting on the mouse.

Re: US Government plans to develop AI that can unmask anonymous writers

#87

Post by ElementaryElk »

PointA2B wrote: post #47
ElementaryElk wrote: post #40

Earlier quoted context omitted.

I’ve found plenty of articles that seem to be run through these spinners, but hand made corrections are likely to be necessary (unless it can be automated with ML for example) as you can almost always tell that something is odd based on context lacking word choices

And thats exactly what newer programs do, look at AppSumo and its practically all of them. The older gen simply used a giant dictionary, then picked a random option from the list of acceptable choices.

Ok, I wasn’t familiar with the newer gen of spinners

Re: US Government plans to develop AI that can unmask anonymous writers

#88

Post by RobRivera »

dehrmann wrote: post #8

Plans? I assumed lots of people were already working on this. There's already a lot of training data out there, and I suspect most users can be identified by use of a handful of uncommon trigrams and sentence stats. I know you can recognize things I've written at work because they have real em dashes—people rarely type with those.

I'm a big counter intelligence man, so I love deliberately inserting randomness into potential identification metrics.

In the words of martha stewart, it's a good thing

Post reply on HN