{"id":"https://openalex.org/W4416549543","doi":"https://doi.org/10.1145/3719027.3744870","title":"Breaking and Fixing Content-Defined Chunking","display_name":"Breaking and Fixing Content-Defined Chunking","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W4416549543","doi":"https://doi.org/10.1145/3719027.3744870"},"language":"en","primary_location":{"id":"doi:10.1145/3719027.3744870","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719027.3744870","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719027.3744870","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3719027.3744870","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115060777","display_name":"Kien Tuong Truong","orcid":"https://orcid.org/0009-0006-9370-9677"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kien Tuong Truong","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0006-9370-9677","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080981496","display_name":"Simon-Philipp Merz","orcid":"https://orcid.org/0000-0002-2475-2966"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Simon-Philipp Merz","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-2475-2966","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019266756","display_name":"Matteo Scarlata","orcid":"https://orcid.org/0009-0000-6285-6259"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matteo Scarlata","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0000-6285-6259","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474325","display_name":"Felix G\u00fcnther","orcid":"https://orcid.org/0000-0002-8495-6610"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Felix G\u00fcnther","raw_affiliation_strings":["IBM Research Europe - Zurich, R\u00fcschlikon, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8495-6610","affiliations":[{"raw_affiliation_string":"IBM Research Europe - Zurich, R\u00fcschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072987600","display_name":"Kenneth G. Paterson","orcid":"https://orcid.org/0000-0002-5145-4489"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kenneth G. Paterson","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5145-4489","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9246,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88823641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2294","last_page":"2308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.3352999985218048,"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"}},"topics":[{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.3352999985218048,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.28519999980926514,"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"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.07769999653100967,"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/exploit","display_name":"Exploit","score":0.7397000193595886},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.6614000201225281},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.6074000000953674},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4284000098705292},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.3188000023365021},{"id":"https://openalex.org/keywords/information-leakage","display_name":"Information leakage","score":0.3124000132083893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486999869346619},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7397000193595886},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.6614000201225281},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.6074000000953674},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C503016453","wikidata":"https://www.wikidata.org/wiki/Q4839801","display_name":"Backup software","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C161615301","wikidata":"https://www.wikidata.org/wiki/Q309396","display_name":"Keystroke logging","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.2680000066757202}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3719027.3744870","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719027.3744870","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719027.3744870","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},{"id":"pmh:doi:10.3929/ethz-b-000748182","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/748182","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3719027.3744870","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719027.3744870","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719027.3744870","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416549543.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W39167138","https://openalex.org/W1553098517","https://openalex.org/W1571203384","https://openalex.org/W1855109561","https://openalex.org/W1916902331","https://openalex.org/W1969335064","https://openalex.org/W2056980397","https://openalex.org/W2059514976","https://openalex.org/W2110322986","https://openalex.org/W2139172211","https://openalex.org/W2157240622","https://openalex.org/W2165257856","https://openalex.org/W2272516773","https://openalex.org/W2545905260","https://openalex.org/W2794517056","https://openalex.org/W2920734175","https://openalex.org/W2965346902","https://openalex.org/W2986445348","https://openalex.org/W4210310743","https://openalex.org/W4385654471"],"related_works":[],"abstract_inverted_index":{"Content-defined":[0],"chunking":[1],"(CDC)":[2],"algorithms":[3],"split":[4],"streams":[5],"of":[6],"data":[7,22,33],"into":[8],"smaller":[9],"blocks,":[10],"called":[11],"chunks,":[12],"in":[13,29],"a":[14],"way":[15],"that":[16,31],"preserves":[17],"chunk":[18,60],"boundaries":[19],"when":[20,52],"the":[21,67],"is":[23,27],"partially":[24],"changed.":[25],"CDC":[26,48],"ubiquitous":[28],"applications":[30],"deduplicate":[32],"such":[34],"as":[35],"backup":[36],"solutions,":[37],"software":[38],"patching":[39],"systems,":[40],"and":[41],"file":[42],"hosting":[43],"platforms.":[44],"Much":[45],"like":[46],"compression,":[47],"can":[49,58],"introduce":[50],"leakage":[51],"combined":[53],"with":[54],"encryption:":[55],"fingerprinting":[56],"attacks":[57],"exploit":[59],"length":[61],"patterns":[62],"to":[63],"infer":[64],"information":[65],"about":[66],"data.":[68]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-23T00:00:00"}
