Reverse engineering Gemini's SynthID detection • Hacker News Board

Re: Reverse engineering Gemini's SynthID detection

#41

Post by akersten » Thu, Apr 09, 2026, 10:59 PM UTC

khernandezrt wrote: post #10

Ok i get that eventually someone was gonna do this but why would we want to purposely remove one of the only ways of detecting if an image is ai generated or not...?

Fundamentally it's a fuzzy signal and people shouldn't rely on it. The general public does not understand Boolean logic (oh, so the SynthID is not there, therefore this image is real). The sooner AI watermarking faces its deserved farcical demise the better.

Also something about how AI is not special and we haven't added or needed invisible watermarks for other ways media can be manipulated deceptively since time immemorial, but that's less of a practical argument and more of a philosophical one.

Re: Reverse engineering Gemini's SynthID detection

#42

Post by StarlaAtNight » Thu, Apr 09, 2026, 11:25 PM UTC

akersten wrote: post #41

khernandezrt wrote: post #10

Ok i get that eventually someone was gonna do this but why would we want to purposely remove one of the only ways of detecting if an image is ai generated or not...?

Fundamentally it's a fuzzy signal and people shouldn't rely on it. The general public does not understand Boolean logic (oh, so the SynthID is not there, therefore this image is real). The sooner AI watermarking faces its deserved farcical demise the better. Also something about how AI is not special and we haven't added or needed invisible watermarks for other ways media can be manipulated deceptively since time imm…

I’m not very well read on the topic and you seen to take a strong “con” stance. Curious to hear why you think it deserves such a demise

Re: Reverse engineering Gemini's SynthID detection

#43

Post by love2read » Thu, Apr 09, 2026, 11:34 PM UTC

ddtaylor wrote: post #36

Tiberium wrote: post #29

Seems like a very low-quality AI-assisted research repo, and it doesn't even properly test against Google's own SynthID detector. It's not hard at all (with some LLM assistance, for example) to reverse-engineer network requests to be able to do SynthID detection without a browser instance or Gemini access, and then you'd have a ground truth.

I read a lot of comments on HN that say something is not hard, yet don't provide a POC of their own or link to research they have knowledge of. I also read a lot of comments on HN that start by attacking the source of the information, such as saying it was AI assisted, instead of the actual merits of the work. The HN community is becoming curmudgeonly and using AI tooling as the justification.

becoming? under most posts that even in passing mention using AI tools there are multiple people raising their noses talking about how much they hate AI use

Re: Reverse engineering Gemini's SynthID detection

#44

Post by love2read » Thu, Apr 09, 2026, 11:36 PM UTC

StarlaAtNight wrote: post #42

akersten wrote: post #41

Earlier quoted context omitted.

Fundamentally it's a fuzzy signal and people shouldn't rely on it. The general public does not understand Boolean logic (oh, so the SynthID is not there, therefore this image is real). The sooner AI watermarking faces its deserved farcical demise the better. Also something about how AI is not special and we haven't added or needed invisible watermarks for other ways media can be manipulated deceptively since time imm…

I’m not very well read on the topic and you seen to take a strong “con” stance. Curious to hear why you think it deserves such a demise

People think that just because they have a way to prove that an image is AI, their worries of misinformation are solved. Better to acknowledge that wherever you look people will be trying to deceive you even if their content won't have as obvious an indicator as SynthID.

Re: Reverse engineering Gemini's SynthID detection

#45

Post by pixl97 » Fri, Apr 10, 2026, 12:01 AM UTC

love2read wrote: post #43

ddtaylor wrote: post #36

Earlier quoted context omitted.

I read a lot of comments on HN that say something is not hard, yet don't provide a POC of their own or link to research they have knowledge of. I also read a lot of comments on HN that start by attacking the source of the information, such as saying it was AI assisted, instead of the actual merits of the work. The HN community is becoming curmudgeonly and using AI tooling as the justification.

becoming? under most posts that even in passing mention using AI tools there are multiple people raising their noses talking about how much they hate AI use

Eh, just the same people that have been killing tech forums and closing posts on stack overflow for like ever.

Re: Reverse engineering Gemini's SynthID detection

#46

Post by pixl97 » Fri, Apr 10, 2026, 12:06 AM UTC

lokar wrote: post #14

khernandezrt wrote: post #10

Ok i get that eventually someone was gonna do this but why would we want to purposely remove one of the only ways of detecting if an image is ai generated or not...?

It was always going to be available to some people, but not everyone would know or believe that. Now they will.

Much like every other thing in the tech world. He'll, it's why AI will kill us off eventually.

If a system depends on every person on the planet not doing one particular thing or the system breaks, expect the system to break quickly.

This is an especially common trope in software. If someone can make software that does something you consider bad, it will happen. Also it's software. There is no difference between it being available to one person or a million. The moment the software exists and can be copied an unbound number of times.

Re: Reverse engineering Gemini's SynthID detection

#47

Post by matthias_m_dev » Fri, Apr 10, 2026, 12:07 AM UTC

[dead]

Re: Reverse engineering Gemini's SynthID detection

#48

Post by pixl97 » Fri, Apr 10, 2026, 12:09 AM UTC

levocardia wrote: post #30

raincole wrote: post #21

Earlier quoted context omitted.

There is no solution . I don't know why people discuss this subject as if there is a technical solution. As if there are fairies or souls hidden in the pixels that help us tell what is AI generated and what is not.

Sure there is a solution, you are just looking at it the wrong way. Make non-AI images provably unaltered with signed keys from the device (e.g. the camera) that took it.