乐胖代购免代理版

{"id":"https://openalex.org/W4386242325","doi":"https://doi.org/10.1145/3600211.3604690","title":"Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models","display_name":"Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models","publication_year":2023,"publication_date":"2023-08-08","ids":{"openalex":"https://openalex.org/W4386242325","doi":"https://doi.org/10.1145/3600211.3604690"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3600211.3604690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1145/3600211.3604690","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049073875","display_name":"Peter Henderson","orcid":"https://orcid.org/0000-0003-3938-0541"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Henderson","raw_affiliation_strings":["Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074009646","display_name":"Eric Mitchell","orcid":"https://orcid.org/0000-0002-7487-1744"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Mitchell","raw_affiliation_strings":["Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Manning","raw_affiliation_strings":["Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087088138","display_name":"Dan Jurafsky","orcid":"https://orcid.org/0000-0002-6459-7745"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Jurafsky","raw_affiliation_strings":["Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Finn","raw_affiliation_strings":["Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.114,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":6,"citation_normalized_percentile":{"value":0.999976,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":92,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"296"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9995,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9995,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9917,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9524,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.47333246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75410223},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6322553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5800591},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.53518575},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4968491},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.47333246},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.45264438},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3600211.3604690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2211.14946","pdf_url":"https://arxiv.org/pdf/2211.14946","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3600211.3604690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":9,"referenced_works":["https://openalex.org/W2189149359","https://openalex.org/W2798658180","https://openalex.org/W2804178350","https://openalex.org/W2909212904","https://openalex.org/W3124700728","https://openalex.org/W3127354108","https://openalex.org/W4220681836","https://openalex.org/W4221104163","https://openalex.org/W4312933868"],"related_works":["https://openalex.org/W4310988119","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W4246396837","https://openalex.org/W3191453585","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W1561927205"],"abstract_inverted_index":{"A":[0],"growing":[1],"ecosystem":[2],"of":[3,37,97],"large,":[4],"open-source":[5,98],"foundation":[6,26,99,112],"models":[7,27,113,136,158],"has":[8],"reduced":[9],"the":[10,35,57,94,106,134,195],"labeled":[11],"data":[12],"and":[13,41,53,75,80,163],"technical":[14],"expertise":[15],"necessary":[16],"to":[17,21,62,120,123,189,198],"apply":[18],"machine":[19,43],"learning":[20,44],"many":[22],"new":[23,87],"problems.":[24],"Yet":[25],"pose":[28],"a":[29,174,183],"clear":[30],"dual-use":[31,65],"risk,":[32],"indiscriminately":[33],"reducing":[34],"costs":[36],"building":[38],"both":[39,78],"harmful":[40,124,149],"beneficial":[42],"systems.":[45],"Policy":[46],"tools":[47,147],"such":[48,64,104],"as":[49],"restricted":[50],"model":[51,185],"access":[52],"export":[54],"controls":[55],"are":[56,114],"primary":[58],"methods":[59],"currently":[60],"used":[61],"mitigate":[63],"risks.":[66],"In":[67,173],"this":[68],"work,":[69],"we":[70,167,177],"review":[71],"potential":[72],"safe-release":[73],"strategies":[74],"argue":[76],"that":[77,142],"policymakers":[79],"AI":[81],"researchers":[82],"would":[83],"benefit":[84],"from":[85,145,161,186],"fundamentally":[86],"technologies":[88],"enabling":[89],"more":[90],"precise":[91],"control":[92],"over":[93],"downstream":[95],"usage":[96],"models.":[100],"We":[101,132,151],"propose":[102],"one":[103],"approach:":[105],"task":[107],"blocking":[108],"paradigm,":[109],"in":[110],"which":[111,166],"trained":[115],"with":[116],"an":[117,153],"additional":[118],"mechanism":[119],"impede":[121],"adaptation":[122],"tasks":[125],"without":[126,193],"sacrificing":[127],"performance":[128],"on":[129],"desirable":[130],"tasks.":[131],"call":[133,168],"resulting":[135],"self-destructing":[137,157],"models,":[138],"inspired":[139],"by":[140],"mechanisms":[141],"prevent":[143,182],"adversaries":[144],"using":[146],"for":[148,155],"purposes.":[150],"present":[152],"algorithm":[154],"training":[156],"leveraging":[159],"techniques":[160],"meta-learning":[162],"adversarial":[164,170],"learning,":[165],"meta-learned":[169],"censoring":[171],"(MLAC).":[172],"small-scale":[175],"experiment,":[176],"show":[178],"MLAC":[179],"can":[180],"largely":[181],"BERT-style":[184],"being":[187],"re-purposed":[188],"perform":[190,199],"gender":[191],"identification":[192],"harming":[194],"model's":[196],"ability":[197],"profession":[200],"classification.":[201]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4386242325","counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-01-05T06:57:44.961842","created_date":"2023-08-30"}