{"id":"https://openalex.org/W2001864643","doi":"https://doi.org/10.1145/1651309.1651317","title":"A targeted web crawling for building malicious javascript collection","display_name":"A targeted web crawling for building malicious javascript collection","publication_year":2009,"publication_date":"2009-11-06","ids":{"openalex":"https://openalex.org/W2001864643","doi":"https://doi.org/10.1145/1651309.1651317","mag":"2001864643"},"language":"en","primary_location":{"id":"doi:10.1145/1651309.1651317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1651309.1651317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM first international workshop on Data-intensive software management and mining","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/A5073854019","display_name":"Peter Likarish","orcid":null},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Likarish","raw_affiliation_strings":["The University of Iowa, Iowa City, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Iowa, Iowa City, USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101809771","display_name":"Eunjin Jung","orcid":"https://orcid.org/0000-0003-1224-4072"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eunjin Jung","raw_affiliation_strings":["The University of Iowa, Iowa City, IA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Iowa, Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7144,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.67112671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/javascript","display_name":"JavaScript","score":0.8465036153793335},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8111979961395264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770121693611145},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7046976089477539},{"id":"https://openalex.org/keywords/botnet","display_name":"Botnet","score":0.6966657638549805},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6544182300567627},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.6361336708068848},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.6336343288421631},{"id":"https://openalex.org/keywords/unobtrusive-javascript","display_name":"Unobtrusive JavaScript","score":0.5736300945281982},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.461538165807724},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.43605679273605347},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4358316659927368},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24901488423347473},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.22318607568740845},{"id":"https://openalex.org/keywords/rich-internet-application","display_name":"Rich Internet application","score":0.06889957189559937}],"concepts":[{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.8465036153793335},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8111979961395264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770121693611145},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7046976089477539},{"id":"https://openalex.org/C22735295","wikidata":"https://www.wikidata.org/wiki/Q317671","display_name":"Botnet","level":3,"score":0.6966657638549805},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6544182300567627},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.6361336708068848},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6336343288421631},{"id":"https://openalex.org/C198240166","wikidata":"https://www.wikidata.org/wiki/Q2298909","display_name":"Unobtrusive JavaScript","level":4,"score":0.5736300945281982},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.461538165807724},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.43605679273605347},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4358316659927368},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24901488423347473},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.22318607568740845},{"id":"https://openalex.org/C103048170","wikidata":"https://www.wikidata.org/wiki/Q725485","display_name":"Rich Internet application","level":3,"score":0.06889957189559937},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1651309.1651317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1651309.1651317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM first international workshop on Data-intensive software management and mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1527571395","https://openalex.org/W1761672165","https://openalex.org/W2032095999","https://openalex.org/W2060857434","https://openalex.org/W2113167642","https://openalex.org/W2156250856","https://openalex.org/W4247465700","https://openalex.org/W6676915735"],"related_works":["https://openalex.org/W650647575","https://openalex.org/W2472584751","https://openalex.org/W2476571673","https://openalex.org/W597036300","https://openalex.org/W827014118","https://openalex.org/W2737557375","https://openalex.org/W648161522","https://openalex.org/W2937855189","https://openalex.org/W605139400","https://openalex.org/W2231287854"],"abstract_inverted_index":{"Malicious":[0],"javascript":[1,18,49],"frequently":[2],"serves":[3],"as":[4,27,39],"a":[5,78],"starting":[6],"point":[7],"of":[8,41,47,86],"web-based":[9],"attacks,":[10],"in":[11,36],"particular":[12],"cross-site":[13],"scripting.":[14],"Thus":[15],"detecting":[16],"malicious":[17,48,66,87],"before":[19],"execution":[20],"can":[21],"protect":[22],"users":[23],"from":[24,34],"attacks":[25,38],"such":[26],"malware":[28],"infection,":[29],"drive-by":[30],"downloads,":[31],"and":[32,65,89],"even":[33],"participating":[35],"denial-of-service":[37],"part":[40],"botnet":[42],"sometimes.":[43],"A":[44],"large":[45],"collection":[46],"would":[50],"help":[51],"with":[52,101],"detector":[53],"development,":[54],"but":[55],"by":[56],"the":[57],"time":[58],"crawler":[59,80,95,99],"arrives":[60],"at":[61],"blacklisted":[62],"domains":[63],"attackers":[64],"scripts":[67],"are":[68],"often":[69],"long":[70],"gone.":[71],"We":[72],"have":[73],"used":[74],"classifiers":[75],"to":[76,98],"direct":[77],"web":[79,94],"better":[81],"towards":[82],"more":[83],"likely":[84],"locations":[85],"scripts,":[88],"show":[90],"how":[91],"this":[92],"targeted":[93],"performs":[96],"compared":[97],"seed":[100],"blacklisted-domains.":[102]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
