I always assumed it was a bit like SHA hashing. Yes, collisions are theoretically possible. But they're so unlikely that it can be used as a unique identifier for most purposes.
this post was submitted on 11 Jan 2024
166 points (88.1% liked)
Technology
34915 readers
34 users here now
This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.
Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.
Rules:
1: All Lemmy rules apply
2: Do not post low effort posts
3: NEVER post naziped*gore stuff
4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.
5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)
6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist
7: crypto related posts, unless essential, are disallowed
founded 5 years ago
MODERATORS
That is not at all what this article is about. The headline is terrible.
The research is suggesting that there may exist "per-person" fingerprint markers, whereas right now we only use "per-finger" markers. It's suggesting that they could look at two different fingers, (left index and right pinky, for example) and say "these two fingerprints are from the same person".
When they say "not unique", they mean "there appear to be markers common to all fingerprints of the same person"
The truth is more interesting than the headline
Precisely. We've always known that identical fingerprints are not just possible but more common than the regular folk would imagine. The point is that the statistical probability of two individuals being in the same room at the same time and related to the same crime with the exact same fingerprints are so low as to make fingerprint ID good enough.
Multiply that by fingerprint evidence being often partial and damaged and how few shits the penal bureaucracy gives about people they've already decided are guilty
~~Excepting of course identical twins~~
Edit: apparently I was wrong
They tend to have different fingerprints for the same reasons they will have differing birthmarks.
Identical twins do not have identical fingerprints, because fingerprints are not only genetic. They might be close or somewhat similar, but rarely identical. They can be distinguished as different individuals by regular pedestrian forensic techniques.
Columbia Engineering senior Aniv Ray and Ph.D. student Judah Goldfeder, who helped analyze the data, noted that their results are just the beginning. "Just imagine how well this will perform once it's trained on millions instead of thousands of fingerprints," said Ray.
Or we're going to find out fingerprint analysis was junk science, just like hair analysis.
We'll still use it to convict people though.
Hair analysis is not good?
Basically, hair doesn't have enough unique characteristics to identify a person and your hair changes all the time depending on diet, age, sun exposure, etc. Lots of shit we use is unreliable: blood-spatter patterns, arson analysis, bite-mark comparisons, and now finger prints!
Have you read the link? It doesn't say thay that analysing figerprints is less powerfull than was known, but more. It describes previously unknown connection between fingerprints of different fingers of a single person. This could indicate, for example, that two crimes were probably commited by the same person even when not a single identical fingerprint was found on both sites.
Seems like pretty flimsy evidence if all we have to go off of is an AI that only gets it right 80% of the time... I highly doubt you could show the 2 fingerprints to anyone else to verify visually, and we're just supposed to trust it?
Well, it wouldn't be good evidence on its own at court, but can very well nudge an investigation in a right direction. And anyway, it's a first step, done with little resources and ablimited dataset for training. And at least for me, it'sbthe first time I hear something like this is possible at all. Others said that tools to the same effect were around for quite a while, but I haven't seen anyone providing sources, especially some that would give quantification of its capabilites.
There has been no science to back up fingerprints being unique enough to determine identity by. I'm not sure "going to find out" is quite the same as "has never been proven to be true."
Imaging explaining to a jury:
A statistical model says that there is a 99% chance these two finger prints belong to the same person. We don't know how this model works and it was not programmed by a human. We will be taking no further questions.
The jury: sounds like magic to me! Sounds good!
If we rig the jury to all be Silicon Valley investors and CEOs, you just have to say "AI" and you'll win the case.
Imagine finding a suspect with this method, and not taking their actual finger prints to check if the match is correct.
They do know how it works: it detected a pattern in the difference between fingers and checks that.
Also this would usually not be needed explained to a jury. If they have the suspect in custody they can just check their fingerprints directly.
You could hypothetically show the jury literally ALL of the math!
yeah, what a feat
Phrenology, voice stress analysis, lie detectors, etc. - There's a long list of things that don't really work being used by law enforcement to help put lot of innocent people in prison.
Fingerprints might not be on the same level of fraudulent bullshit of the above, but they also shouldn't be the unquestionable end-all be-all of proof either.
They aren't on the same level of fraudulent bullshit, but they're close.
Fingerprint matching is done "by eye" and often involves an "expert" saying that one smudge is a 100% match for another smudge.
DNA matching is the only forensic science that's worth a damn, and only if it's done correctly.
DNA matching is the only forensic science that's worth a damn, and only if it's done correctly.
And even that one is useless in case of identical twins.
The article headline is misleading. Nothing in the study indicates that fingerprints can't be used to uniquely identity people. It claims to show that although each fingerprint on a single person is unique, they have similar features. Thus, one could assess whether a pair of fingerprints come from the same person.
Yeah, "discovers"... what we've known for a long time. But buzzword in the title = clicks (& thus money from ads on the page) so there's that.
They have a specific result though, which is that fingerprints from different fingers of the same person tend to be recognizable as coming from the same person, just from their characteristics. Was that also known for a long time?
Yes, it has been know since forever. It's not like every finger is a different being. There are three well known chemicals related to the creation of fingerprints patterns. We have sequenced the RNA responsible for determining both the timing and concentrations of these three chemicals. We know thus that people's fingerprints all have certain commonalities that can be used to identify that two, different, fingerprints came from the same person. It has been used by police forces for at least a decade now.
If you read about Turing patterns you'll learn more and be already way ahead of these dude's research. They are trying to parade undergrad knowledge under the AI umbrella. Maybe if they knew a thing or two about forensics they would've made a better contribution to science.
The article makes a big point about how this result is not common knowledge and not the commonly accepted viewpoint. To the extent that their paper was rejected for it. Are you saying they made that up?
I haven't read their paper but... the idea that vaccines can prevent against diseases without harmful side effects is also "not common knowledge" fwiw (the level of basic science literacy in most of the Western world is abysmal), and if reviewers rejected the paper then there is a good chance that there is a reason for that.
If you are interested in this topic, here is an excellent (imho) summary video from 6 years ago, which around 9:30 talks about this identical topic. Enjoy! :-) Beware though, from someone who has been down that road: it will make you sad, and the more you learn along these lines, the less hope it will leave you that anything will ever be okay again:-(. I cannot emphasize this enough: I am nowhere close to kidding here.
They copy pasted the Columbia University press release word for word. Which is unfortunately way too common on science journalism. The article just repeats the researchers claims which may or may not hold water. Their main claim that they proved that inter fingerprints aren't unique is just semantic manipulation. That's probably what irked reviewers. Their research doesn't support their claims. At best, they're proposing a mediocre application of AI to detect markers that were already known about.
That makes a lot of sense. It's way too easy to spread BS the way that science journalism works.
Congratulations to AI researchers for figuring something we knew pretty much since the first proposal of fingerprinting as a bio ID tech. We know that fingerprints aren't unique. That's why they're being rejected everywhere. They don't know what they're talking about and refuse to work out how their research fits into established forensics knowledge. They have no prior knowledge about forensics and insist on overturning decades of forensic knowledge with "I don't know, something with the curvatures of the lines inside the fingerprints, I guess. We don't actually know what the AI model is doing."
The title of the article is so misleading it's pretty much wrong.
If you read the article, what the researchers did was train an AI model that appears to be able to associate different fingerprints of the SAME person.
Example:Assume your finger prints are not on record. You do a crime and you accidentally leave a fingerprint of your left index finger at the scene.
THEN you do another crime and leave your RIGHT MIDDLE finger print at the scene.
The premise is that the AI model appears to be able to correlate DIFFERENT prints from the SAME person.
So, I'm the context of the research, they aren't saying that there is reason to believe that there exist fingerprint markers that might be present on a per-person basis, rather than strictly a per-finger basis.
Terrible headline, terribly written article, and IMO not nearly enough evidence that the correlation actually exists and even less evidence that it's appropriate to be able to be used as evidence.
That being said, based on the comments in the comments section I think most people didn't really grok what this research was, which is understandable based on the terrible headline
The research is bogus then as well. Projections like those have been in wide use at police stations around the globe at least since my cousin bragged about having this when he started his police training. That was.2008.
I mean, the research is the research and the data is the data.
If there are specific critiques to the methodology of the research that calls the validity of the observed data into question, that's fair. "It's 'well known' that..." Isn't a scientific argument. It's actually the exact opposite, it's literally religion.
Also, the conclusions being drawn from the data by the researchers or 3rd parties might be a problem.
To be fair, ML of today is unrecognizable to what it was in 2008. And, I'd be willing to bet the model your cousin was exposed to wasn't a machine learning model, and instead some handcrafted marker analysis with dubious justification but a great sales team.
The great thing about ML science is that it's super accessible. This was an undergrad project. The next step, to establish the validity, really just requires a larger data set. If it's bogus, that'll come out. If it's valid, that'll come out too. The cost of reproducibility is so low that even hobbiests can verify the results.
My cousin wasn't using any ML model. Their software probably did a geometric projection and that's it. Then they'd search for the proposed owner of the fingerprint and get the real ones to compare against. That's something that ML models cannot take from police as long as long as hallucinating is possible.
Right, so this methodology is a completely different approach. I don't think it's fair to call snake oil on this specifically with the justification that other models (using an entirely different approach) were.
Again, not saying it's real or not, I'm just saying that it's appropriate to try new approaches to examine things we already THINK we know, and to be prepared to carefully and fairly evaluate new data that calls into question things we thought we knew. That's just science.
I agree with you. But still, none of what they are talking about is new in the slightest. We know from research on the genetic markers, that determine skin cell differentiation, that people's fingerprints from different fingers have commonalities. Since they were formed by the same chemical signals with roughly the same timing. There's a lot of science on that pathway with RNA sequencing and Turing pattern research. But these authors obviously ignore all of that.
They explain poorly what they are doing because they don't understand what they are doing or how it relates to forensic science. None of the researchers has any experience with forensics. They are just a bunch of dudes playing with computers, AI and a dataset. Rightfully their research was rejected by all major forensic journals.
load more comments
(2 replies)
The article is about matching different fingerprints from different fingers of the same person (something we apparently thought wasn’t possible) rather than finding different people who share fingerprints. AI can do it with 77% accuracy which they say isn’t enough to convict someone by itself but could help with narrowing leads.
I kinda assumed this was the case, and some higher ups likely know this too. I know in Ontario, when you get fingerprinted by the police, it's not just your fingers, they'll take your whole palm print. Billions of people in the world, very unlikely anyone is 100% unique.
That wasn't really their finding though. They found that the AI could recognize when different fingerprints came from different fingers of the same person.
I think we all just look alike to our computer overlords.