Large companies have no problem scraping data to be used to train their models, but they don't seem to feel the same way about you scraping theirs.
Using ‘radioactive data’ to detect if a data set was used for training
21–30 of 30 posts
Re: Using ‘radioactive data’ to detect if a data set was used for training
#22I can see a similar technique in use to detect cheaters in Kaggle competitions.
Re: Using ‘radioactive data’ to detect if a data set was used for training
#23Not mentioned thus far anywhere in the article or in comments: potentially weaponizing this against deep fakes. What's to stop cameras from making raw photos "radioactive" from now on, making deepfakes traceable by tainting the image-sets on which the models generating the deepfakes were trained? This isn't my field. I'm certain there's a workaround, but I'd suspect detecting sufficiently well-placed markers would re…
Printer manufacturers have been doing this [1] for a long time.
1 - https://en.wikipedia.org/wiki/Machine_Identification_Code
Re: Using ‘radioactive data’ to detect if a data set was used for training
#24Not mentioned thus far anywhere in the article or in comments: potentially weaponizing this against deep fakes. What's to stop cameras from making raw photos "radioactive" from now on, making deepfakes traceable by tainting the image-sets on which the models generating the deepfakes were trained? This isn't my field. I'm certain there's a workaround, but I'd suspect detecting sufficiently well-placed markers would re…
Printer manufacturers have been doing this [1] for a long time. 1 - https://en.wikipedia.org/wiki/Machine_Identification_Code
Yep, one of the reasons color printers can't print black+white without yellow present.
Re: Using ‘radioactive data’ to detect if a data set was used for training
#25Ctrl+f shows no mention of the study of post-processing quantization nor pruning on their tampered dataset.
Overall, I instinctively think that one can create an NN architecture that is not affected, or even easily detect the tampered pictures with a pre processing pass, and untamper them.
NN are actually fuzzy, they support noise, you could add a bit more noise in the dataset to defeat the "radioactiveness".
Also, I'm pretty sure Facebook is not doing it to protect user data, but I have no proof.
Re: Using ‘radioactive data’ to detect if a data set was used for training
#26This is a major plot point in Accelerando.
Re: Using ‘radioactive data’ to detect if a data set was used for training
#27This is a major plot point in Accelerando.
I've read Accelerando and don't remember a major plot point that remotely looks like this. Perhaps are you thinking of one of the many secondary plot points.
Can you elaborate? Chapter? Context? Thanks.
Re: Using ‘radioactive data’ to detect if a data set was used for training
#28Not relevant to the main trust of the article but barium sulphate is not radioactive, it just efficiently absorbs X-rays. Radioactive markers are I believe most commonly used in PET scans, Wikipedia suggests flourine-18 as the common isotope used.
you are very correct - authors are doing a fascinating and smart parallel, but the analogy (contrast X-RAY imaging) is wrong. A radioactive element (F-18) marking a glucose molecule for tracking sugar metabolism in the human body with an imager (PET) is what they mean. This is one of many techniques in the field of nuclear medicine or molecular imaging.
Re: Using ‘radioactive data’ to detect if a data set was used for training
#29This is a major plot point in Accelerando.
I've read Accelerando and don't remember a major plot point that remotely looks like this. Perhaps are you thinking of one of the many secondary plot points. Can you elaborate? Chapter? Context? Thanks.
First chapter; the lobsters are afraid of steganographic covert channels in the training data for their translator:
> Manfred drains his beer glass, sets it down, stands up, and begins to walk along the main road, phone glued to the side of his head. He wraps his throat mike around the cheap black plastic casing, pipes the input to a simple listener process. "Are you saying you taught yourself the language just so you could talk to me?"
> "Da, was easy: Spawn billion-node neural network, and download Teletubbies and Sesame Street at maximum speed. Pardon excuse entropy overlay of bad grammar: Am afraid of digital fingerprints steganographically masked into my-our tutorials."
I guess it would have only been a major plot point if the digital fingerprints had turned out to be present and had tripped some kind of monitoring system.
Re: Using ‘radioactive data’ to detect if a data set was used for training
#30Ctrl+f shows no mention of the study of post-processing quantization nor pruning on their tampered dataset. Overall, I instinctively think that one can create an NN architecture that is not affected, or even easily detect the tampered pictures with a pre processing pass, and untamper them. NN are actually fuzzy, they support noise, you could add a bit more noise in the dataset to defeat the "radioactiveness". Also, I…
but the noise FB adds is weighted a special way