Can you share some sources? I would be extremely surprised if such fine grained noise survives imagine compression to the extent that you could identify the source of an imagine despite changing lighting conditions, locations, exposure times, etc

A kagi search found this paper that achieved decent results on youtube compression, 5 years ago https://arxiv.org/abs/2012.06277

There are tons of results (and papers) if you google/kagi: "image noise fingerprint ccd sensor". I smell lazyness here.