{"id":"https://openalex.org/W3003244330","doi":"https://doi.org/10.1109/icdse47409.2019.8971481","title":"An Empirical Study to Detect the Collision Rate in Similarity Hashing Algorithm Using MD5","display_name":"An Empirical Study to Detect the Collision Rate in Similarity Hashing Algorithm Using MD5","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W3003244330","doi":"https://doi.org/10.1109/icdse47409.2019.8971481","mag":"3003244330"},"language":"en","primary_location":{"id":"doi:10.1109/icdse47409.2019.8971481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdse47409.2019.8971481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Data Science and Engineering (ICDSE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075218655","display_name":"Tushaar Gangavarapu","orcid":"https://orcid.org/0000-0002-0489-9573"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushaar Gangavarapu","raw_affiliation_strings":["Worldwide Deals, Automated Advertising, Amazon.com, Inc.,Bangalore,India","Worldwide Deals, Automated Advertising, Amazon.com, Inc., Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worldwide Deals, Automated Advertising, Amazon.com, Inc.,Bangalore,India","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Worldwide Deals, Automated Advertising, Amazon.com, Inc., Bangalore, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054016512","display_name":"C. D. Jaidhar","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C.D. Jaidhar","raw_affiliation_strings":["National Institute of Technology Karnataka,Department of Information Technology,Mangalore,India","National Institute of Technology Karnataka, Mangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Karnataka,Department of Information Technology,Mangalore,India","institution_ids":["https://openalex.org/I11880225"]},{"raw_affiliation_string":"National Institute of Technology Karnataka, Mangalore, India","institution_ids":["https://openalex.org/I11880225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.18719706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10951","display_name":"Cryptographic Implementations and Security","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10951","display_name":"Cryptographic Implementations and Security","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11017","display_name":"Chaos-based Image/Signal Encryption","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.8647170066833496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8027932643890381},{"id":"https://openalex.org/keywords/md5","display_name":"MD5","score":0.7499009966850281},{"id":"https://openalex.org/keywords/cryptographic-hash-function","display_name":"Cryptographic hash function","score":0.6776986122131348},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.5543404221534729},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5453289747238159},{"id":"https://openalex.org/keywords/digital-signature","display_name":"Digital signature","score":0.504637598991394},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.492303729057312},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.48300278186798096},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4777459502220154},{"id":"https://openalex.org/keywords/collision-detection","display_name":"Collision detection","score":0.462016224861145},{"id":"https://openalex.org/keywords/collision-resistance","display_name":"Collision resistance","score":0.4579232633113861},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38481417298316956},{"id":"https://openalex.org/keywords/cryptography","display_name":"Cryptography","score":0.3547465205192566},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.317861407995224},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.27649205923080444}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.8647170066833496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027932643890381},{"id":"https://openalex.org/C157172786","wikidata":"https://www.wikidata.org/wiki/Q185235","display_name":"MD5","level":3,"score":0.7499009966850281},{"id":"https://openalex.org/C7608002","wikidata":"https://www.wikidata.org/wiki/Q477202","display_name":"Cryptographic hash function","level":3,"score":0.6776986122131348},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.5543404221534729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5453289747238159},{"id":"https://openalex.org/C118463975","wikidata":"https://www.wikidata.org/wiki/Q220849","display_name":"Digital signature","level":3,"score":0.504637598991394},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.492303729057312},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.48300278186798096},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4777459502220154},{"id":"https://openalex.org/C199668693","wikidata":"https://www.wikidata.org/wiki/Q1550329","display_name":"Collision detection","level":3,"score":0.462016224861145},{"id":"https://openalex.org/C150909736","wikidata":"https://www.wikidata.org/wiki/Q1779448","display_name":"Collision resistance","level":5,"score":0.4579232633113861},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38481417298316956},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.3547465205192566},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.317861407995224},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.27649205923080444},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdse47409.2019.8971481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdse47409.2019.8971481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Data Science and Engineering (ICDSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W79931031","https://openalex.org/W124337392","https://openalex.org/W1542068190","https://openalex.org/W1595429669","https://openalex.org/W1656678770","https://openalex.org/W1656731780","https://openalex.org/W1660562555","https://openalex.org/W2012833704","https://openalex.org/W2055625904","https://openalex.org/W2086659222","https://openalex.org/W2096929438","https://openalex.org/W2098801947","https://openalex.org/W2103239853","https://openalex.org/W2120058970","https://openalex.org/W2133252868","https://openalex.org/W2145349611","https://openalex.org/W2293617401","https://openalex.org/W2441697793","https://openalex.org/W2916086000","https://openalex.org/W2945159763","https://openalex.org/W2953648974","https://openalex.org/W3145042860","https://openalex.org/W4230940751","https://openalex.org/W4231078754","https://openalex.org/W6603338000","https://openalex.org/W6605092562","https://openalex.org/W6674755139","https://openalex.org/W6679821486","https://openalex.org/W6718844653"],"related_works":["https://openalex.org/W2464389987","https://openalex.org/W3019245231","https://openalex.org/W1487949331","https://openalex.org/W1546067676","https://openalex.org/W2620584623","https://openalex.org/W1974544592","https://openalex.org/W3114065414","https://openalex.org/W122749164","https://openalex.org/W2782107767","https://openalex.org/W1512443456"],"abstract_inverted_index":{"Similarity":[0],"Hashing":[1],"(SimHash)":[2],"is":[3,30,53,60,90,155],"a":[4,31,142,175],"widely":[5],"used":[6,40],"locality-sensitive":[7],"hashing":[8],"algorithm":[9],"employed":[10,91],"in":[11,16,46,161,182,189],"the":[12,43,70,83,94,97,119,139,187,190,193],"detection":[13,22,84,128,154],"of":[14,34,85,96,178,192],"similarity,":[15],"large-scale":[17],"data":[18],"processing,":[19],"including":[20],"plagiarism":[21],"and":[23,113,133,149,167],"near-duplicate":[24],"web":[25],"document":[26],"detection.":[27],"Collision":[28,153],"resistance":[29],"crucial":[32],"property":[33],"cryptographic":[35],"hash":[36,51,68,121],"algorithms":[37],"that":[38,67],"are":[39],"to":[41,55,62,69,81,92,111,124,158,180],"verify":[42],"message":[44],"integrity":[45,95],"internet":[47],"security":[48],"applications.":[49],"A":[50],"function":[52],"said":[54],"be":[56],"collision-resistant":[57],"if":[58],"it":[59],"hard":[61],"find":[63],"two":[64],"different":[65],"inputs":[66],"same":[71],"output.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76,137],"present":[77],"an":[78],"empirical":[79,172],"study":[80,173],"facilitate":[82],"collision":[86,127,176],"rate":[87,177],"when":[88],"SimHash":[89,183],"check":[93],"message.":[98],"The":[99],"analysis":[100],"was":[101],"performed":[102],"using":[103,141],"bit":[104,194],"sequences":[105],"with":[106,129,146,186],"length":[107,191],"varying":[108],"from":[109],"2":[110],"32":[112],"Message":[114],"Digest":[115],"5":[116],"(MD5)":[117],"as":[118],"internal":[120],"function.":[122],"Furthermore,":[123],"enable":[125],"faster":[126],"more":[130],"significant":[131],"speedup":[132],"efficient":[134],"space":[135],"utilization,":[136],"parallelized":[138],"process":[140],"distributed":[143,168],"data-parallel":[144],"approach":[145],"synchronous":[147],"computation":[148],"optimum":[150],"load":[151],"balancing.":[152],"desirable,":[156],"owing":[157],"its":[159],"applicability":[160],"digital":[162],"signature":[163],"systems,":[164,166],"proof-of-work":[165],"content":[169],"systems.":[170],"Our":[171],"revealed":[174],"0%":[179],"0.048%":[181],"(with":[184],"MD5)":[185],"variation":[188],"sequence.":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}