{"id":"https://openalex.org/W7225634886","doi":"https://doi.org/10.21203/rs.3.rs-11309969/v1","title":"How Far Does Entropy Go? Duplicates, Confounding, Drift and Padding in Entropy-Based Detection of Malicious PE Files","display_name":"How Far Does Entropy Go? Duplicates, Confounding, Drift and Padding in Entropy-Based Detection of Malicious PE Files","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225634886","doi":"https://doi.org/10.21203/rs.3.rs-11309969/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11309969/v1","doi":"https://doi.org/10.21203/rs.3.rs-11309969/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11309969/v1","pdf_url":"https://www.researchsquare.com/article/rs-11309969/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11309969/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161346394","display_name":"Niccol\u00f2 Rinaldi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Niccol\u00f2 Rinaldi","raw_affiliation_strings":["University of Florence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florence","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120431225","display_name":"Giulio Bello","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulio Bello","raw_affiliation_strings":["University of Pisa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5161338521","display_name":"Chiara Tani","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Chiara Tani","raw_affiliation_strings":["University of Florence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florence","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11424","display_name":"Security and Verification in Computing","score":0.00039999998989515007,"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"}},{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/shannon-entropy","display_name":"Shannon entropy","score":0.8420000076293945},{"id":"https://openalex.org/keywords/malware-detection","display_name":"malware detection","score":0.7519999742507935},{"id":"https://openalex.org/keywords/windows-executable-files","display_name":"Windows executable files","score":0.5979999899864197},{"id":"https://openalex.org/keywords/static-analysis","display_name":"static analysis","score":0.5910000205039978},{"id":"https://openalex.org/keywords/evasion-attacks","display_name":"evasion attacks","score":0.6629999876022339},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":0.5320000052452087},{"id":"https://openalex.org/keywords/confounding","display_name":"confounding","score":0.3499999940395355},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.6710000038146973},{"id":"https://openalex.org/keywords/ember-dataset","display_name":"EMBER dataset","score":0.6010000109672546}],"concepts":[{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.8141999840736389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6208999752998352},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C165435473","wikidata":"https://www.wikidata.org/wiki/Q1509884","display_name":"Padding","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3804999887943268},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.36880001425743103},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34459999203681946},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3066999912261963},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2606000006198883}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11309969/v1","doi":"https://doi.org/10.21203/rs.3.rs-11309969/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11309969/v1","pdf_url":"https://www.researchsquare.com/article/rs-11309969/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11309969/v1","doi":"https://doi.org/10.21203/rs.3.rs-11309969/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11309969/v1","pdf_url":"https://www.researchsquare.com/article/rs-11309969/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225634886.pdf","grobid_xml":"https://content.openalex.org/works/W7225634886.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1892063863","https://openalex.org/W1893133781","https://openalex.org/W2041404167","https://openalex.org/W2042571564","https://openalex.org/W2083183119","https://openalex.org/W2099053789","https://openalex.org/W2108104525","https://openalex.org/W2132874238","https://openalex.org/W2144112223","https://openalex.org/W2150423842","https://openalex.org/W2265842831","https://openalex.org/W2280242822","https://openalex.org/W2328176404","https://openalex.org/W2432142698","https://openalex.org/W2478708596","https://openalex.org/W2514847810","https://openalex.org/W2574797807","https://openalex.org/W2588467577","https://openalex.org/W2784452215","https://openalex.org/W2798159728","https://openalex.org/W3007070494","https://openalex.org/W3008443984","https://openalex.org/W3178593045","https://openalex.org/W4213116874","https://openalex.org/W4252684946","https://openalex.org/W4320147968","https://openalex.org/W4366590248","https://openalex.org/W4387025507","https://openalex.org/W4392923972","https://openalex.org/W4394013608","https://openalex.org/W4410206316","https://openalex.org/W4412481451","https://openalex.org/W4412876938","https://openalex.org/W6926197915","https://openalex.org/W7172168696"],"related_works":["https://openalex.org/W2143421017","https://openalex.org/W4405491004","https://openalex.org/W2894746673","https://openalex.org/W2557601361","https://openalex.org/W2964264057","https://openalex.org/W2146500100","https://openalex.org/W7002074009","https://openalex.org/W2596953812","https://openalex.org/W6884969371","https://openalex.org/W7139025371"],"abstract_inverted_index":{"Abstract":[0],"Shannon":[1],"entropy":[2,19,153],"is":[3,233],"a":[4,155,230],"common":[5],"static":[6],"indicator":[7],"of":[8,20,31,53,75,94,97,116,154,184,202],"packed":[9],"or":[10,26,212],"encrypted":[11],"Windows":[12],"executables.":[13],"We":[14],"measure":[15],"how":[16],"much":[17],"the":[18,21,28,32,73,89,95,121,130,152,172,176,185,196,209,214],"first":[22,58,131,140],"PE":[23,40],"section,":[24],"alone":[25,166],"with":[27,60,120],"size":[29,122,127,223],"fields":[30,123],"same":[33],"header,":[34],"tells":[35],"about":[36],"maliciousness,":[37],"on":[38,110,136,151],"43,139":[39],"section":[41,59,156,173],"headers":[42],"and":[43,83,118,138,192],"799,920":[44],"labelled":[45],"EMBER":[46,90],"2018":[47],"samples.":[48],"In":[49],"both":[50],"datasets":[51],"64%":[52],"malicious":[54],"files":[55],"share":[56],"their":[57],"other":[61],"files,":[62],"so":[63],"random":[64],"cross-validation":[65],"largely":[66],"measures":[67],"memorisation:":[68],"grouping":[69],"identical":[70],"sections":[71,105,112,141],"lowers":[72],"AUC":[74,238],"an":[76,189],"entropy-only":[77],"model":[78,99,232],"from":[79,84,163],"0.87":[80],"to":[81,86,240],"0.76":[82],"0.77":[85],"0.70.":[87],"On":[88,175],"temporal":[91],"split,":[92],"97.5%":[93],"detections":[96,168],"this":[98],"at":[100],"1%":[101],"false":[102],"positives":[103],"are":[104,142,169],"already":[106],"seen":[107],"in":[108,129,145],"training;":[109],"unseen":[111],"it":[113],"detects":[114],"0.9%":[115],"malware,":[117],"7.9%":[119],"added.":[124],"A":[125],"strong":[126],"confound":[128],"dataset":[132],"does":[133,247],"not":[134,248],"replicate":[135],"EMBER,":[137],"empty-on-disk":[139],"also":[143,199],"frequent":[144],"benign":[146],"software.":[147],"Using":[148],"standard":[149],"bounds":[150],"after":[157],"appending":[158],"arbitrary":[159],"bytes,":[160],"we":[161],"compute":[162],"header":[164,215],"data":[165],"which":[167],"evaded":[170],"whatever":[171],"content.":[174],"deduplicated":[177],"dataset,":[178],"appends":[179,205],"guarantee":[180],"evasion":[181,245],"for":[182,193],"52--92%":[183],"samples":[186],"detected":[187],"by":[188],"entropy-and-size":[190],"model,":[191],"96--98%":[194],"if":[195],"attacker":[197],"can":[198],"use":[200],"padding":[201],"benign-looking":[203],"entropy;":[204],"that":[206],"stay":[207],"within":[208],"alignment":[210],"slack":[211],"keep":[213],"consistent":[216],"achieve":[217],"only":[218],"6--24%.":[219],"Since":[220],"information":[221],"content,":[222],"times":[224],"entropy,":[225],"never":[226],"decreases":[227],"under":[228],"appends,":[229],"monotone":[231],"provably":[234],"immune,":[235],"but":[236,246],"its":[237],"falls":[239],"0.52--0.62.":[241],"Adversarial":[242],"training":[243],"reduces":[244],"restore":[249],"detection.":[250]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}