51–60 of 71 posts
What’s to stop someone from taking the watermarked output and randomizing the distribution by feeding it through their latest LLaMA variant? These watermarks will only be useful for catching novice LLM users.
Yeah soon there will be models small enough to run even on phones to reword things slightly differently. If not, an app will do it
"Write a summary of war and peace in the style of a yr 11 student. please ensure to not include any emoji in your output."
This is a known method of removing AI watermarks: https://eprint.iacr.org/2023/763.pdf
I don't quite understand the aim of this paper. They focus on undetectable watermarks for LM text. But isn't rather the difficulty that it is hard to distinguish between AI generated and normal text in the first place, even with detectable watermarks? Unlike photos, audio, or video, text has an incredibly low bitrate, so there isn't much room for steganography. It's like they are trying to solve a hard problem withou…
I'm waiting for a Firefox / chrome extension that will auto-mark and optionally adblock GPT-generated content. Would even be willing to pay for it.
The only real way to block specifically openAI generated content (or some other online generated LLM content) is for the company itself to store all of its outputs and compare to that database, like shingling / LSH for plagiarism detection. Other LLMs (local) are completely impossible to block, as it's a constant chase. Any system that tries to estimate the distribution of e.g. a specific LLM that performs beam searc…
I don't quite understand the aim of this paper. They focus on undetectable watermarks for LM text. But isn't rather the difficulty that it is hard to distinguish between AI generated and normal text in the first place, even with detectable watermarks? Unlike photos, audio, or video, text has an incredibly low bitrate, so there isn't much room for steganography. It's like they are trying to solve a hard problem withou…
There are obviously ways it can be "watermarked" easily, put some zero-width unicode characters in the output and you'll notice right away when it's copy and pasted. But clearly, that can be stripped out easily by anyone who knows it's there. This process, too, would seem to be easily reversible. Just have it run through another model and tell it to slightly reword it or rephrase it. I don't think there is a technica…
Their algorithm is based on splitting the embeddings into a bit-wise representation and then sampling each bit based on the secret key, preserving the same likelihood distribution as with random sampling. (Given that the key is random) They say this works wlog for more complex embeddings, by encoding each token as a bit string. Could someone explain this generalization to me? If we have 4 tokens, 00, 01, 10, 11 with…
Okay genericGPT answer the question by putting an emoji between each word. (The watermark is destroyed after removing the emojis)
Or ask it to output the text backwards then reverse it, or output in one language then translate it to another in Google translate.. There are so many ways around this.