{"id":"https://openalex.org/W4311165761","doi":"https://doi.org/10.1145/3564625.3567986","title":"NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks","display_name":"NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks","publication_year":2022,"publication_date":"2022-12-03","ids":{"openalex":"https://openalex.org/W4311165761","doi":"https://doi.org/10.1145/3564625.3567986"},"language":"en","primary_location":{"id":"doi:10.1145/3564625.3567986","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3564625.3567986","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3564625.3567986","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 38th Annual Computer Security Applications Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3564625.3567986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048064145","display_name":"Nuo Xu","orcid":"https://orcid.org/0000-0001-6148-2830"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nuo Xu","raw_affiliation_strings":["Lehigh University, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6148-2830","affiliations":[{"raw_affiliation_string":"Lehigh University, United States of America","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789833","display_name":"Binghui Wang","orcid":"https://orcid.org/0000-0001-5616-060X"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Binghui Wang","raw_affiliation_strings":["Illinois Institute of Technology, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-5616-060X","affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, United States of America","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083888171","display_name":"Ran Ran","orcid":"https://orcid.org/0000-0002-6112-5013"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ran Ran","raw_affiliation_strings":["Lehigh University, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-6112-5013","affiliations":[{"raw_affiliation_string":"Lehigh University, United States of America","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103129518","display_name":"Wujie Wen","orcid":"https://orcid.org/0000-0003-3440-1905"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wujie Wen","raw_affiliation_strings":["Lehigh University, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3440-1905","affiliations":[{"raw_affiliation_string":"Lehigh University, United States of America","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014965408","display_name":"Parv Venkitasubramaniam","orcid":"https://orcid.org/0000-0002-0999-3331"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parv Venkitasubramaniam","raw_affiliation_strings":["Lehigh University, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-0999-3331","affiliations":[{"raw_affiliation_string":"Lehigh University, United States of America","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.012,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78714612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"669","last_page":"683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9986000061035156,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7730509042739868},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6390211582183838},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6056382656097412},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.600699245929718},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5850939750671387},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5830693244934082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5564708709716797},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4873269498348236},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.48083624243736267},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4647350311279297},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4244341254234314},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15768861770629883},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11530691385269165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730509042739868},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6390211582183838},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6056382656097412},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.600699245929718},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5850939750671387},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5830693244934082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5564708709716797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4873269498348236},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.48083624243736267},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4647350311279297},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4244341254234314},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15768861770629883},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11530691385269165},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3564625.3567986","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3564625.3567986","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3564625.3567986","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 38th Annual Computer Security Applications Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.05565","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.05565","pdf_url":"https://arxiv.org/pdf/2206.05565","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3564625.3567986","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3564625.3567986","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3564625.3567986","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 38th Annual Computer Security Applications Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G2544598470","display_name":"SPX: Collaborative Research: Scalable Neural Network Paradigms to Address Variability in Emerging Device based Platforms for Large Scale Neuromorphic Computing","funder_award_id":"2006748","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7827079726","display_name":"SHF: Small: Collaborative Research: Retraining-free Concurrent Test and Diagnosis in Emerging Neural Network Accelerators","funder_award_id":"2011236","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311165761.pdf","grobid_xml":"https://content.openalex.org/works/W4311165761.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W602971198","https://openalex.org/W1473189865","https://openalex.org/W1607198972","https://openalex.org/W1821462560","https://openalex.org/W1873763122","https://openalex.org/W1985511977","https://openalex.org/W2051267297","https://openalex.org/W2095705004","https://openalex.org/W2182467309","https://openalex.org/W2183341477","https://openalex.org/W2471517265","https://openalex.org/W2473418344","https://openalex.org/W2535690855","https://openalex.org/W2561238782","https://openalex.org/W2604776663","https://openalex.org/W2618530766","https://openalex.org/W2701059868","https://openalex.org/W2752929869","https://openalex.org/W2795435272","https://openalex.org/W2798657499","https://openalex.org/W2884280357","https://openalex.org/W2884943453","https://openalex.org/W2887995258","https://openalex.org/W2912023992","https://openalex.org/W2927692314","https://openalex.org/W2930926105","https://openalex.org/W2932329902","https://openalex.org/W2946363484","https://openalex.org/W2956128647","https://openalex.org/W2963143631","https://openalex.org/W2963378725","https://openalex.org/W2963456518","https://openalex.org/W2963857521","https://openalex.org/W2964318098","https://openalex.org/W2973232880","https://openalex.org/W2977730164","https://openalex.org/W2979479162","https://openalex.org/W2983140679","https://openalex.org/W3004170295","https://openalex.org/W3013068160","https://openalex.org/W3013700197","https://openalex.org/W3071470454","https://openalex.org/W3082950354","https://openalex.org/W3102360395","https://openalex.org/W3104224589","https://openalex.org/W3104591140","https://openalex.org/W3105067168","https://openalex.org/W3106873467","https://openalex.org/W3115042282","https://openalex.org/W3118608800","https://openalex.org/W3124987929","https://openalex.org/W3137695714","https://openalex.org/W3138758728","https://openalex.org/W3169818958","https://openalex.org/W3170901302","https://openalex.org/W3205533264","https://openalex.org/W3208549305","https://openalex.org/W3214437258","https://openalex.org/W4221154610","https://openalex.org/W4288103499","https://openalex.org/W4288563649","https://openalex.org/W4295312788"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1482441085","https://openalex.org/W2966858528","https://openalex.org/W2151687600"],"abstract_inverted_index":{"Membership":[0],"inference":[1,42],"attacks":[2],"(MIAs)":[3],"against":[4,25,63,144],"machine":[5],"learning":[6],"models":[7],"lead":[8],"to":[9,87,99],"serious":[10],"privacy":[11],"risks":[12],"for":[13],"the":[14,19,90,111,156,172],"training":[15,40,75,94],"dataset":[16],"used":[17],"in":[18,48,74,82,119],"model":[20,72,78,91],"training.":[21],"The":[22],"state-of-the-art":[23,142,173],"defenses":[24,143,174],"MIAs":[26,154],"often":[27],"suffer":[28],"from":[29],"poor":[30],"privacy-utility":[31],"balance":[32],"and":[33,56,96,116,130,138,182],"defense":[34],"generality,":[35,181],"as":[36,38],"well":[37],"high":[39],"or":[41,76],"overhead.":[43,183],"To":[44],"overcome":[45],"these":[46],"limitations,":[47],"this":[49],"paper,":[50],"we":[51],"propose":[52],"a":[53,104],"novel,":[54],"lightweight":[55],"effective":[57],"Neuron-Guided":[58],"Defense":[59],"method":[60],"named":[61],"NeuGuard":[62,85,137,170],"MIAs.":[64],"Unlike":[65],"existing":[66],"solutions":[67],"which":[68],"either":[69],"regularize":[70],"all":[71],"parameters":[73],"noise":[77],"output":[79,92,114,133],"per":[80],"input":[81],"real-time":[83],"inference,":[84],"aims":[86],"wisely":[88],"guide":[89],"of":[93,113],"set":[95,98],"testing":[97],"have":[100],"close":[101],"distributions":[102],"through":[103],"fine-grained":[105],"neuron":[106],"regularization.":[107],"That":[108],"is,":[109],"restricting":[110],"activation":[112],"neurons":[115,118],"inner":[117],"each":[120],"layer":[121],"simultaneously":[122],"by":[123,175],"using":[124],"our":[125],"developed":[126],"class-wise":[127],"variance":[128],"minimization":[129],"layer-wise":[131],"balanced":[132],"control.":[134],"We":[135],"evaluate":[136],"compare":[139],"it":[140],"with":[141],"two":[145],"neural":[146],"network":[147],"based":[148,153],"MIAs,":[149],"five":[150],"strongest":[151],"metric":[152],"including":[155],"newly":[157],"proposed":[158],"label-only":[159],"MIA":[160],"on":[161],"three":[162],"benchmark":[163],"datasets.":[164],"Extensive":[165],"experimental":[166],"results":[167],"show":[168],"that":[169],"outperforms":[171],"offering":[176],"much":[177],"improved":[178],"utility-privacy":[179],"trade-off,":[180],"Our":[184],"code":[185],"is":[186],"publicly":[187],"available":[188],"at":[189],"https://github.com/nux219/NeuGuard.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}