▲ 704 ▼ Recreating uncensored Epstein PDFs from raw encoded attachments (neosmart.net) submitted 9 months ago by apftwb@lemmy.world to c/technology@lemmy.world 57 comments fedilink hide all child comments
[–] RIotingPacifist@lemmy.world 11 points 9 months ago (5 children) How big is N though? permalink fedilink source parent hideshow 5 child comments replies: [–] Qwaffle_waffle@sh.itjust.works 11 points 9 months ago 64 permalink fedilink source parent [–] mEEGal@lemmy.world 5 points 9 months ago Asking the real questions permalink fedilink source parent [–] hodgepodgin@lemmy.zip 1 point 9 months ago (2 children) Since there’s 78 pages, I’m guessing at least 1 ambiguity per page? Anyways, it’s dreadfully big. permalink fedilink source parent hideshow 2 child comments replies: [–] RIotingPacifist@lemmy.world 2 points 9 months ago (1 child) 2^78 is large but computers can do an awful lot per second, so if only about some the pages contain attachments 2^40-55 is something you could bruteforce in weeks if you can do millions of attempts a second permalink fedilink source parent hideshow 1 child comment replies: [–] vatlark@lemmy.world 1 point 9 months ago I have never looked into the details of an OCR, but if it's a classifier it should give the it's confidence in being a 1 or L so you can start with the low confidence characters. permalink fedilink source parent
[–] mEEGal@lemmy.world 5 points 9 months ago Asking the real questions permalink fedilink source parent
[–] hodgepodgin@lemmy.zip 1 point 9 months ago (2 children) Since there’s 78 pages, I’m guessing at least 1 ambiguity per page? Anyways, it’s dreadfully big. permalink fedilink source parent hideshow 2 child comments replies: [–] RIotingPacifist@lemmy.world 2 points 9 months ago (1 child) 2^78 is large but computers can do an awful lot per second, so if only about some the pages contain attachments 2^40-55 is something you could bruteforce in weeks if you can do millions of attempts a second permalink fedilink source parent hideshow 1 child comment replies: [–] vatlark@lemmy.world 1 point 9 months ago I have never looked into the details of an OCR, but if it's a classifier it should give the it's confidence in being a 1 or L so you can start with the low confidence characters. permalink fedilink source parent
[–] RIotingPacifist@lemmy.world 2 points 9 months ago (1 child) 2^78 is large but computers can do an awful lot per second, so if only about some the pages contain attachments 2^40-55 is something you could bruteforce in weeks if you can do millions of attempts a second permalink fedilink source parent hideshow 1 child comment replies: [–] vatlark@lemmy.world 1 point 9 months ago I have never looked into the details of an OCR, but if it's a classifier it should give the it's confidence in being a 1 or L so you can start with the low confidence characters. permalink fedilink source parent
[–] vatlark@lemmy.world 1 point 9 months ago I have never looked into the details of an OCR, but if it's a classifier it should give the it's confidence in being a 1 or L so you can start with the low confidence characters. permalink fedilink source parent