{"id":"https://openalex.org/W4396821636","doi":"https://doi.org/10.1145/3630106.3658936","title":"Silencing the Risk, Not the Whistle: A Semi-automated Text Sanitization Tool for Mitigating the Risk of Whistleblower Re-Identification","display_name":"Silencing the Risk, Not the Whistle: A Semi-automated Text Sanitization Tool for Mitigating the Risk of Whistleblower Re-Identification","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4396821636","doi":"https://doi.org/10.1145/3630106.3658936"},"language":"en","primary_location":{"id":"doi:10.1145/3630106.3658936","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658936","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658936","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658936","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049421291","display_name":"Dimitri Staufer","orcid":"https://orcid.org/0009-0000-1671-222X"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dimitri Staufer","raw_affiliation_strings":["TU Berlin, Germany"],"raw_orcid":"https://orcid.org/0009-0000-1671-222X","affiliations":[{"raw_affiliation_string":"TU Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063320659","display_name":"Frank Pallas","orcid":"https://orcid.org/0000-0002-5543-0265"},"institutions":[{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Frank Pallas","raw_affiliation_strings":["Paris Lodron University Salzburg, Austria"],"raw_orcid":"https://orcid.org/0000-0002-5543-0265","affiliations":[{"raw_affiliation_string":"Paris Lodron University Salzburg, Austria","institution_ids":["https://openalex.org/I182212641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072130052","display_name":"Bettina Berendt","orcid":"https://orcid.org/0000-0002-8003-3413"},"institutions":[{"id":"https://openalex.org/I4210117750","display_name":"Weizenbaum Institute","ror":"https://ror.org/023kksk09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I176453806","https://openalex.org/I2800804238","https://openalex.org/I2801702882","https://openalex.org/I315704651","https://openalex.org/I4210117750","https://openalex.org/I4577782","https://openalex.org/I46043019","https://openalex.org/I4923324","https://openalex.org/I75951250"]},{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE","DE"],"is_corresponding":false,"raw_author_name":"Bettina Berendt","raw_affiliation_strings":["TU Berlin, Germany and Weizenbaum Institute, Germany and KU Leuven, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-8003-3413","affiliations":[{"raw_affiliation_string":"TU Berlin, Germany and Weizenbaum Institute, Germany and KU Leuven, Belgium","institution_ids":["https://openalex.org/I4210117750","https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.564,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69717618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"733","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9944999814033508,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9944999814033508,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.988099992275238,"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/T11492","display_name":"Academic integrity and plagiarism","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7119801640510559},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.676301121711731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6692721247673035},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5263903141021729},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.5137792229652405},{"id":"https://openalex.org/keywords/anonymity","display_name":"Anonymity","score":0.48401686549186707},{"id":"https://openalex.org/keywords/accountability","display_name":"Accountability","score":0.48322996497154236},{"id":"https://openalex.org/keywords/writing-style","display_name":"Writing style","score":0.4179067611694336},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3732357621192932},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.34616392850875854},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.16575458645820618},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.14785411953926086},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.13220176100730896},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11604413390159607}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7119801640510559},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.676301121711731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692721247673035},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5263903141021729},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.5137792229652405},{"id":"https://openalex.org/C178005623","wikidata":"https://www.wikidata.org/wiki/Q308859","display_name":"Anonymity","level":2,"score":0.48401686549186707},{"id":"https://openalex.org/C2776007630","wikidata":"https://www.wikidata.org/wiki/Q2798912","display_name":"Accountability","level":2,"score":0.48322996497154236},{"id":"https://openalex.org/C13622073","wikidata":"https://www.wikidata.org/wiki/Q2243831","display_name":"Writing style","level":2,"score":0.4179067611694336},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3732357621192932},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.34616392850875854},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.16575458645820618},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.14785411953926086},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.13220176100730896},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11604413390159607},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3630106.3658936","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658936","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658936","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.01097","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.01097","pdf_url":"https://arxiv.org/pdf/2405.01097","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:weizenbaum-library.de:id/860","is_oa":true,"landing_page_url":"https://www.weizenbaum-library.de/handle/id/860","pdf_url":null,"source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3630106.3658936","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658936","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658936","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396821636.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W630110518","https://openalex.org/W1034374084","https://openalex.org/W1171432701","https://openalex.org/W1511575487","https://openalex.org/W1690606251","https://openalex.org/W1977913639","https://openalex.org/W2017725764","https://openalex.org/W2024228866","https://openalex.org/W2064301261","https://openalex.org/W2085106103","https://openalex.org/W2103577799","https://openalex.org/W2105646944","https://openalex.org/W2134167315","https://openalex.org/W2136114025","https://openalex.org/W2166226940","https://openalex.org/W2531621976","https://openalex.org/W2541018429","https://openalex.org/W2621075239","https://openalex.org/W2804992248","https://openalex.org/W2886358838","https://openalex.org/W2901147448","https://openalex.org/W2939865804","https://openalex.org/W2963515066","https://openalex.org/W2963956191","https://openalex.org/W2991848153","https://openalex.org/W2995465878","https://openalex.org/W3005930749","https://openalex.org/W3012137864","https://openalex.org/W3094917620","https://openalex.org/W3119000130","https://openalex.org/W3134356368","https://openalex.org/W3208051580","https://openalex.org/W4205974944","https://openalex.org/W4229069570","https://openalex.org/W4238846128","https://openalex.org/W4240224338","https://openalex.org/W4292793781","https://openalex.org/W4294982692","https://openalex.org/W4306878170","https://openalex.org/W6630594124","https://openalex.org/W6810950096","https://openalex.org/W6824583106"],"related_works":["https://openalex.org/W2494121465","https://openalex.org/W4377233172","https://openalex.org/W1854749775","https://openalex.org/W4312971597","https://openalex.org/W2129556718","https://openalex.org/W1970818898","https://openalex.org/W2350665531","https://openalex.org/W2906160980","https://openalex.org/W2154949144","https://openalex.org/W3199802296"],"abstract_inverted_index":{"Whistleblowing":[0],"is":[1,121],"essential":[2],"for":[3,68,123,153,203],"ensuring":[4],"transparency":[5],"and":[6,11,32,56,83,106,112,145,150,166,178,210,228,235,243],"accountability":[7],"in":[8,53,133,160],"both":[9],"public":[10],"private":[12],"sectors.":[13],"However,":[14,74],"(potential)":[15],"whistleblowers":[16,70],"often":[17],"fear":[18],"or":[19],"face":[20],"retaliation,":[21],"even":[22],"when":[23],"reporting":[24],"anonymously.":[25],"The":[26],"specific":[27],"content":[28],"of":[29,89,109,163,224,256,276,288],"their":[30,33,54],"disclosures":[31],"distinct":[34],"writing":[35,139],"style":[36],"may":[37],"re-identify":[38],"them":[39],"as":[40,46,103,281],"the":[41,47,124,137,158,161,164,175,221,237,248,277,284],"source.":[42],"Legal":[43],"measures,":[44],"such":[45],"EU":[48],"Whistleblower":[49],"Directive,":[50],"are":[51,64],"limited":[52,87],"scope":[55],"effectiveness.":[57],"Therefore,":[58,141],"computational":[59],"methods":[60],"to":[61,71,93,183,205,269,274],"prevent":[62],"re-identification":[63,131],"important":[65],"complementary":[66],"tools":[67,78],"encouraging":[69],"come":[72],"forward.":[73],"current":[75],"text":[76,208],"sanitization":[77],"follow":[79],"a":[80,147,185,195,231],"one-size-fits-all":[81],"approach":[82],"take":[84],"an":[85,118],"overly":[86],"view":[88],"anonymity.":[90],"They":[91],"aim":[92],"mitigate":[94],"identification":[95],"risk":[96,165,173],"by":[97,283],"replacing":[98],"typical":[99],"high-risk":[100],"words":[101],"(such":[102],"person":[104],"names":[105],"other":[107],"labels":[108],"named":[110],"entities)":[111],"combinations":[113],"thereof":[114],"with":[115],"placeholders.":[116],"Such":[117],"approach,":[119],"however,":[120],"inadequate":[122],"whistleblowing":[125],"scenario":[126],"since":[127],"it":[128],"neglects":[129],"further":[130],"potential":[132],"textual":[134],"features,":[135],"including":[136],"whistleblower\u2019s":[138],"style.":[140],"we":[142,201],"propose,":[143],"implement,":[144],"evaluate":[146,213],"novel":[148],"classification":[149],"mitigation":[151],"strategy":[152],"rewriting":[154],"texts":[155],"that":[156,200],"involves":[157],"whistleblower":[159,233],"assessment":[162],"utility.":[167],"Our":[168,259],"prototypical":[169],"tool":[170],"semi-automatically":[171],"evaluates":[172],"at":[174],"word/term":[176],"level":[177],"applies":[179],"risk-adapted":[180],"anonymization":[181],"techniques":[182],"produce":[184],"grammatically":[186],"disjointed":[187],"yet":[188],"appropriately":[189],"sanitized":[190],"text.":[191],"We":[192,212],"then":[193],"use":[194],"Large":[196],"Language":[197],"Model":[198],"(LLM)":[199],"fine-tuned":[202],"paraphrasing":[204],"render":[206],"this":[207],"coherent":[209],"style-neutral.":[211],"our":[214],"tool\u2019s":[215],"effectiveness":[216],"using":[217,247],"court":[218],"cases":[219],"from":[220,230,267],"European":[222],"Court":[223],"Human":[225],"Rights":[226],"(ECHR)":[227],"excerpts":[229],"real-world":[232],"testimony":[234],"measure":[236],"protection":[238],"against":[239],"authorship":[240,264],"attribution":[241,265],"attacks":[242],"utility":[244],"loss":[245],"statistically":[246],"popular":[249],"IMDb62":[250],"movie":[251],"reviews":[252],"dataset,":[253],"which":[254],"consists":[255],"62":[257],"individuals.":[258],"method":[260],"can":[261],"significantly":[262],"reduce":[263],"accuracy":[266],"98.81%":[268],"31.22%,":[270],"while":[271],"preserving":[272],"up":[273],"73.1%":[275],"original":[278],"content\u2019s":[279],"semantics,":[280],"measured":[282],"established":[285],"cosine":[286],"similarity":[287],"sentence":[289],"embeddings.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2024-05-11T00:00:00"}
