[{"data":1,"prerenderedAt":583},["ShallowReactive",2],{"project-32002555":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":34,"aspects":35,"strip":49,"post_text":50,"what":51,"said":70,"maker_in_thread":180,"shape":191,"grid":196,"attempts":545,"same_week":546,"maker_shows":38,"maker_hidden":575,"reader_version":576,"card":577},"32002555","human eyes only","PDFs that are readable by human eyes only","title","Show HN: PDFs that are readable by human eyes only","https:\u002F\u002Fhumaneyesonly.com","humaneyesonly.com","viggity",1657121938,2022,216,126,255,2570,10,"notable","security_privacy","document obfuscation","web_app",[24,25,26,27],"pdf obfuscation","ocr resistant pdf","scraper protection","glyph remapping","roasted",-0.518,{"positive":31,"neutral":32,"mixed":31,"critical":33},4,15,52,75,{"performance":36,"design":39,"privacy":41,"idea":43,"execution":46,"docs":47},{"positive":37,"critical":38},0,2,{"positive":40,"critical":31},1,{"positive":37,"critical":42},18,{"positive":44,"critical":45},3,12,{"positive":37,"critical":18},{"positive":37,"critical":48},5,[40,40,40,37,37,40,40,44,40,38,40,40,40,40,40,40,40,40,40,40,40,37,44,40,37,40,38,40,40,40,40,40,40,38,40,38,40,48,48,38],"Hi, OP here. A friend was involved in a custody battle and was afraid his ex was going to leak all of his discovery documents on the internet and he asked if there was something I could do to make it harder for bots\u002Fcrawlers to find sensitive information. Originally I was going to turn all of his docs to image based PDFs, but those get large fast and are easy to OCR.\n\nSo I found a post musing about altering fonts\u002Fglyphs so that it looks like english, but the actual character being seen by the pdf reader is a non-english character. As such, when you try to OCR these files, it doesn't see any im",{"problem":52,"audience":58,"pricing":62,"motivation":63,"time_to_build":62,"stack":67,"openness":68,"stage":69,"team_size":68},{"value":53,"source":54,"evidence":55},"Stops bots and crawlers from finding sensitive text in PDFs such as discovery documents","maker",[56],{"id":57},"post",{"value":59,"source":54,"evidence":60},"People sharing sensitive documents, like a friend in a custody battle",[61],{"id":57},null,{"value":64,"source":54,"evidence":65},"A friend feared his ex-spouse would leak custody discovery documents online",[66],{"id":57},[],"unknown","launched",{"praise":71,"objections":94,"requests":144,"questions":149,"alternatives":157},[72,83],{"value":73,"source":74,"evidence":75},"Clever, elegant approach to thwarting non-targeted scrapers","commenter",[76,80],{"id":77,"by":78,"text":79},"32003377","jffry","I think people will get tripped up by you saying it \"can't\" be OCR'd or that it is difficult to do so, and will end up looking past a pretty elegant solution in the process. This…",{"id":81,"by":11,"text":82},"32003209","It takes the embedded font out of your PDF, and then maps non-latin characters (japanese, cyrillic, etc) to render as if they looked like a latin character. So in the example on…",{"value":84,"source":74,"evidence":85},"Polished site and implementation",[86,90],{"id":87,"by":88,"text":89},"32008531","loxias","I like your intent (helping your friend), and I'm _REALLY_ impressed at the polish (clever name, nice looking website, convert-for-free microservice) but I'm sad to report (like…",{"id":91,"by":92,"text":93},"32006427","hexo","Impressive, the example web text area is very lovely too",[95,114,129,140],{"value":96,"source":74,"evidence":97},"Built-in or standard OCR (rasterize then OCR) defeats it easily",[98,102,106,110],{"id":99,"by":100,"text":101},"32007483","bscphil","This is broken in multiple ways, some obvious, some not. 1. Obviously most people jumped directly to OCR, and that works of course. So counter to the OP, you can trivially render…",{"id":103,"by":104,"text":105},"32003012","solardev","> As such, when you try to OCR these files, it doesn't see any images and can't convert it. That isn't true. Acrobat might skip parts of the PDF that it thinks are already…",{"id":107,"by":108,"text":109},"32008668","hartator","Using CLI OCR, I am getting a 100% match: `Name: Satoshi Nakamoto DOB: 1982-06-05 SSN: 958-20-3141 Cell Phone: 514-867-5309`",{"id":111,"by":112,"text":113},"32007625","s1mon","MacOS does OCR on this just fine. Screenshot, open in Preview, and select, copy, paste: Name: Satoshi Nakamoto DOB: 1982-06-05 SSN: 958-20-3141 Cell Phone: 514-867-5309",{"value":115,"source":74,"evidence":116},"Harms accessibility for screen readers and copy-paste",[117,121,125],{"id":118,"by":119,"text":120},"32006431","dawnerd","This is terrible for accessibility, please don't do this.",{"id":122,"by":123,"text":124},"32012754","justshowpost","The reason - to make it only readable by human eyes - doesn’t make sense. It is always only ever readable by human eyes since bots don’t have eyes. You don’t mean eyes, but…",{"id":126,"by":127,"text":128},"32006805","ctoth","I am a blind user using an extension to my screen reader which (under the covers) uses the Windows 10 built-in OCR. Your sample document gives me: INTRODUCTION The Cybersecurity…",{"value":130,"source":74,"evidence":131},"Name and framing are misleading about OCR",[132,136],{"id":133,"by":134,"text":135},"32003938","bil7","I understand that. And I understand your personal use case was valid. But I think your \"Human Eyes Only\" name and domain is a little deceptive.",{"id":137,"by":138,"text":139},"32003663","bambax","Of course. The OP doesn't understand what \"OCR\" actually means.",{"value":141,"source":74,"evidence":142},"Substitution cipher is trivially broken by frequency analysis",[143],{"id":99,"by":100,"text":101},[145],{"value":146,"source":74,"evidence":147},"Suggestions for stronger OCR-resistant transforms",[148],{"id":87,"by":88,"text":89},[150],{"value":151,"source":74,"evidence":152},"How does the mapping work",[153],{"id":154,"by":155,"text":156},"32002915","maybeiambatman","Fascinating. How does this work?",[158,169,176],{"value":159,"source":74,"evidence":160},"Password-protected PDFs and watermarks",[161,165],{"id":162,"by":163,"text":164},"32009624","hda2","Password-protect (i.e. encrypt) the documents and provide the passwords on a separate piece of paper with your reasoning and concerns clearly laid out. This won't prevent the…",{"id":166,"by":167,"text":168},"32008689","schoen","> afraid his ex was going to leak all of his discovery documents on the internet Any chance of getting a clear protective order in advance from the judge, and then enforcing that…",{"value":170,"source":74,"evidence":171},"ZXX typeface",[172],{"id":173,"by":174,"text":175},"32006629","layer8","You could use the ZXX typeface to defy OCR: https:\u002F\u002Fwalkerart.org\u002Fmagazine\u002Fsang-mun-defiant-typeface-nsa-privacy It’s probably still not ML-resistant.",{"value":177,"source":74,"evidence":178},"Protective court orders",[179],{"id":166,"by":167,"text":168},{"comments":32,"answered":31,"key":181},[182,185,188],{"id":183,"text":184},"32007524","very interesting. the windows 10 screen reader consume the raster data on PDFs to OCR and not the code point data embedded within the PDF. People here have been on my ass about…",{"id":186,"text":187},"32008332","Interesting how the screen reader will use the raster image for a PDF but not for the website. Based on the work I had to do to get the PDF to work, PDFs are a clusterfuck of…",{"id":189,"text":190},"32007657","so one thing that I do to counter point 3 is by having multiple non-english characters map to the same english character and I pick a random one each time. Depending on the…",{"commenters":192,"max_depth":193,"maker_replies":32,"first_comment_mins":194,"lifespan_hours":195},82,7,24,29,[197,199,201,204,205,208,212,216,218,222,225,228,231,233,236,238,240,242,245,248,250,253,256,260,262,265,266,269,272,273,277,281,284,287,289,293,294,298,301,303,306,308,312,315,317,320,324,326,328,330,333,336,338,339,342,344,345,348,351,354,357,360,363,366,369,372,374,377,380,383,385,388,390,393,396,400,403,406,408,410,412,414,417,420,424,427,431,433,435,437,438,440,442,444,448,452,454,458,461,463,466,470,472,474,477,479,482,484,486,490,494,498,501,505,507,511,515,519,523,527,530,532,533,535,537,541],[126,37,40,198,127,37],"project\u002Fcritical\u002Fperformance",[183,37,37,200,11,40],"maker\u002Fneutral\u002Fnone",[202,37,40,203,127,37],"32007717","project\u002Fcritical\u002Fdesign",[186,37,37,200,11,40],[206,37,40,207,104,37],"32008567","project\u002Fcritical\u002Fprivacy",[209,37,40,210,211,37],"32010102","project\u002Fcritical\u002Fidea","weird-eye-issue",[213,37,44,214,215,37],"32009873","project\u002Fneutral\u002Fperformance","jasomill",[99,40,40,217,100,37],"project\u002Fcritical\u002Fexecution",[219,40,37,220,221,37],"32007595","commenter\u002Fneutral\u002Fnone","rmbyrro",[223,40,37,220,224,37],"32009154","mdaniel",[226,40,37,220,227,37],"32009478","hunterb123",[229,40,37,220,230,37],"32009482","xwdv",[232,40,37,220,221,37],"32013577",[234,40,37,220,235,37],"32019392","lwswl",[189,40,37,237,11,40],"project\u002Fneutral\u002Fexecution",[239,40,40,207,100,37],"32007807",[241,40,37,237,11,40],"32008348",[243,40,37,220,244,37],"32009495","pwg",[246,40,40,207,247,37],"32007910","ChristopherDrum",[249,40,40,207,100,37],"32008669",[251,40,40,207,252,37],"32011081","davidhbolton",[254,40,37,220,255,37],"32008177","danielrhodes",[257,40,44,258,259,37],"32011674","project\u002Fneutral\u002Fidea","maxloh",[87,38,44,261,88,37],"project\u002Fmixed\u002Fidea",[263,38,37,264,104,37],"32008749","other\u002Fneutral\u002Fnone",[103,44,40,207,104,37],[267,31,37,220,268,37],"32003265","dodo6502",[270,31,37,220,271,37],"32013290","revolvingocelot",[162,48,44,258,163,37],[274,275,40,207,276,37],"32006123",6,"nemothekid",[278,275,44,279,280,37],"32006419","project\u002Fneutral\u002Fprivacy","social_quotient",[282,275,40,207,283,37],"32006699","ben_w",[285,275,40,207,286,37],"32006702","nmstoker",[288,275,37,200,11,40],"32007550",[290,275,40,291,292,37],"32007651","project\u002Fcritical\u002Fdocs","SilasX",[77,193,44,261,78,37],[295,296,40,291,297,37],"32003489",8,"forgotpwd16",[299,300,40,207,104,37],"32002969",9,[302,300,37,200,11,40],"32003116",[304,300,40,291,305,37],"32003191","rst",[307,300,37,220,104,37],"32003237",[309,300,44,310,311,37],"32006597","project\u002Fmixed\u002Fprivacy","RajT88",[313,18,40,207,314,37],"32004932","mmastrac",[316,18,37,220,174,37],"32006458",[318,18,37,220,319,37],"32008901","jagger27",[321,322,40,207,323,37],"32002963",11,"blitz_skull",[325,322,37,200,11,40],"32003066",[327,322,37,220,134,37],"32003127",[329,322,37,200,11,40],"32003392",[331,322,40,207,332,37],"32003632","mbreese",[334,322,40,207,335,37],"32003643","Semaphor",[337,322,37,220,138,37],"32003888",[133,322,40,291,134,37],[340,322,37,220,341,37],"32003183","boloust",[343,322,40,207,104,37],"32003197",[137,322,37,220,138,37],[346,322,40,207,347,37],"32003259","3jckd",[349,322,40,207,350,37],"32003284","thrown_22",[352,322,40,207,353,37],"32003379","gundamdoubleO",[355,322,40,356,335,37],"32003610","maker\u002Fcritical\u002Fnone",[358,322,37,220,359,37],"32006689","vehemenz",[361,322,40,291,362,37],"32006902","SigmundA",[364,322,40,217,365,37],"32008315","abalaji",[367,322,40,217,368,37],"32003076","jfk13",[370,322,44,237,371,37],"32007071","tyingq",[373,45,40,217,350,37],"32003196",[375,45,37,376,11,40],"32003236","maker\u002Fneutral\u002Fdocs",[378,45,37,379,350,37],"32003321","commenter\u002Fneutral\u002Fdocs",[381,45,37,220,382,37],"32005914","smegsicle",[384,45,37,220,350,37],"32008429",[386,45,37,220,387,37],"32003360","kube-system",[173,389,44,258,174,37],13,[391,389,40,217,392,37],"32007833","rafram",[394,389,37,264,395,37],"32008189","jeroenhd",[397,398,40,210,399,37],"32003123",14,"josephcsible",[401,398,37,220,402,37],"32003306","maxbond",[404,398,37,220,405,37],"32003464","withinboredom",[407,398,37,220,402,37],"32005358",[409,398,37,220,399,37],"32008583",[411,398,37,220,402,37],"32008730",[413,398,40,210,399,37],"32009614",[415,398,40,210,416,37],"32003476","kolanos",[418,398,40,210,419,37],"32003384","ck2",[421,32,48,422,423,37],"32004760","project\u002Fpositive\u002Fidea","ksaj",[425,32,37,426,11,40],"32004876","maker\u002Fneutral\u002Fidea",[428,429,37,264,430,37],"32002973",16,"londons_explore",[432,429,37,200,11,40],"32003091",[434,429,40,210,332,37],"32003872",[166,436,37,264,167,37],17,[111,42,40,217,112,37],[118,439,40,203,119,37],19,[441,439,37,220,359,37],"32006536",[443,439,40,203,119,37],"32007605",[445,446,44,258,447,37],"32003074",20,"O__________O",[449,450,37,264,451,37],"32010466",21,"ehhthing",[453,450,37,264,259,37],"32011764",[455,456,40,210,457,37],"32006909",22,"peetah",[459,456,37,460,11,40],"32009355","maker\u002Fpositive\u002Fnone",[122,462,40,210,123,37],23,[464,194,40,210,465,37],"32010559","bryanrasmussen",[467,468,40,217,469,37],"32003092",25,"anyfactor",[471,468,44,237,104,37],"32003138",[473,468,40,217,469,37],"32003248",[475,468,44,476,104,37],"32003283","maker\u002Fneutral\u002Fexecution",[478,468,37,237,11,40],"32003342",[480,468,40,210,481,37],"32004220","salawat",[483,468,44,237,297,37],"32003411",[485,468,37,476,11,40],"32003155",[487,488,44,237,489,37],"32009744",26,"cordite",[491,492,40,210,493,37],"32011744",27,"secretsatan",[495,496,40,210,497,37],"32015057",28,"badrabbit",[499,195,44,237,500,37],"32007845","donkarma",[502,503,44,237,504,37],"32014939",30,"hedora",[107,506,40,217,108,37],31,[508,509,37,264,510,37],"32006510",32,"hk1337",[512,513,40,203,514,37],"32003558",33,"peanut_worm",[516,517,37,264,518,37],"32003243",34,"oxff",[520,521,48,422,522,37],"32009537",35,"oa335",[524,525,44,237,526,37],"32008614",36,"Pakdef",[91,528,48,529,92,37],37,"project\u002Fpositive\u002Fdesign",[154,531,44,258,155,37],38,[81,531,37,237,11,40],[534,531,40,217,138,37],"32003839",[536,531,44,261,382,37],"32004274",[538,539,48,422,540,37],"32002987",39,"waynesonfire",[542,543,40,198,544,37],"32006198",40,"Komodai",[],[547,551,556,561,566,571],{"id":548,"name":549,"points":550,"category":20},"31988820","pamspy",235,{"id":552,"name":553,"points":554,"category":555},"32005678","C3",182,"languages",{"id":557,"name":558,"points":559,"category":560},"31958823","Copper",146,"dev_tools",{"id":562,"name":563,"points":564,"category":565},"31932434","Featureform",136,"ai",{"id":567,"name":568,"points":569,"category":570},"32001817","SPS2022",132,"web_saas",{"id":572,"name":573,"points":574,"category":560},"31936356","UI Filler",129,false,"v2",{"id":578,"name":5,"line":6,"ai":575,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":579,"top":18,"kw":580,"maker":11,"domain":10,"tier":19,"attempts":37,"strip":581,"url":9,"mix":582,"praise":73,"objection":96,"sub":21},32002555,-0.52,[24,25,26,27],"1110011312111111111110310121111112121552",[31,32,31,33],1793991048377]