{"id":"https://openalex.org/W4387870582","doi":"https://doi.org/10.1109/mlsp55844.2023.10286008","title":"A BIC-Based Mixture Model Defense Against Data Poisoning Attacks on Classifiers","display_name":"A BIC-Based Mixture Model Defense Against Data Poisoning Attacks on Classifiers","publication_year":2023,"publication_date":"2023-09-17","ids":{"openalex":"https://openalex.org/W4387870582","doi":"https://doi.org/10.1109/mlsp55844.2023.10286008"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55844.2023.10286008","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp55844.2023.10286008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5100407758","display_name":"Xi Li","orcid":"https://orcid.org/0000-0003-3023-1662"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xi Li","raw_affiliation_strings":["Pennsylvania State University,the School of EECS,University Park,PA,16802"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University,the School of EECS,University Park,PA,16802","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739086","display_name":"David J. Miller","orcid":"https://orcid.org/0000-0001-8848-1643"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David J. Miller","raw_affiliation_strings":["Pennsylvania State University,the School of EECS,University Park,PA,16802"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University,the School of EECS,University Park,PA,16802","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085283385","display_name":"Zhen Xiang","orcid":"https://orcid.org/0000-0002-4284-2041"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Xiang","raw_affiliation_strings":["Pennsylvania State University,the School of EECS,University Park,PA,16802"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University,the School of EECS,University Park,PA,16802","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063903486","display_name":"George Kesidis","orcid":"https://orcid.org/0000-0001-7947-8127"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Kesidis","raw_affiliation_strings":["Pennsylvania State University,the School of EECS,University Park,PA,16802"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University,the School of EECS,University Park,PA,16802","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100407758"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13561035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9958999752998352,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9858999848365784,"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/computer-science","display_name":"Computer science","score":0.5969357490539551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45856818556785583},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3794868588447571}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5969357490539551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45856818556785583},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3794868588447571}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp55844.2023.10286008","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp55844.2023.10286008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2049633694","https://openalex.org/W2064675550","https://openalex.org/W2107397716","https://openalex.org/W2107551505","https://openalex.org/W2142405592","https://openalex.org/W2159294971","https://openalex.org/W2167529272","https://openalex.org/W2168175751","https://openalex.org/W2187013920","https://openalex.org/W2194775991","https://openalex.org/W2509109313","https://openalex.org/W2750650104","https://openalex.org/W2785325870","https://openalex.org/W2790483052","https://openalex.org/W2799244375","https://openalex.org/W2963618920","https://openalex.org/W2964043980","https://openalex.org/W2965721472","https://openalex.org/W3007264885","https://openalex.org/W3007358161","https://openalex.org/W3097922432","https://openalex.org/W3118608800","https://openalex.org/W3122796494","https://openalex.org/W3163222347","https://openalex.org/W4221151475","https://openalex.org/W4239510810","https://openalex.org/W4301880089","https://openalex.org/W6683272254","https://openalex.org/W6686674283","https://openalex.org/W6725794477","https://openalex.org/W6747899497","https://openalex.org/W6748556508","https://openalex.org/W6749755156","https://openalex.org/W6774177702","https://openalex.org/W6789206308","https://openalex.org/W6810206781"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Data":[0],"Poisoning":[1],"(DP)":[2],"is":[3,49],"an":[4,25,55],"effective":[5],"attack":[6,17],"which":[7],"degrades":[8],"a":[9,56,73,88],"trained":[10],"classifier\u2019s":[11],"accuracy":[12],"through":[13],"covert":[14],"injection":[15],"of":[16,60,91,119],"samples":[18,53,86,101],"into":[19],"the":[20,40,51,61,92,104,109,117],"training":[21,62,111],"set.":[22,112],"We":[23],"propose":[24],"unsupervised":[26],"Bayesian":[27],"Information":[28],"Criterion":[29],"(BIC)-based":[30],"mixture":[31,74,93],"model":[32,75],"defense":[33,121],"against":[34],"DP":[35,44,48,124],"attacks":[36],"that:":[37],"1)":[38],"addresses":[39],"most":[41],"challenging":[42],"embedded":[43],"scenario":[45],"wherein,":[46],"if":[47],"present,":[50],"poisoned":[52,85,98],"are":[54],"priori":[57],"unknown":[58],"subset":[59,90],"set,":[63],"and":[64,83,100],"with":[65],"no":[66],"clean":[67],"validation":[68],"set":[69],"available;":[70],"2)":[71],"applies":[72],"to":[76],"both":[77],"well-fit":[78],"potentially":[79],"multi-modal":[80],"class":[81],"distributions":[82],"capture":[84],"within":[87],"small":[89],"components;":[94],"3)":[95],"jointly":[96],"identifies":[97],"components":[99],"by":[102],"minimizing":[103],"BIC":[105],"cost":[106],"defined":[107],"over":[108,131],"whole":[110],"Our":[113],"experimental":[114],"results":[115],"demonstrate":[116],"effectiveness":[118],"our":[120],"under":[122],"strong":[123],"attacks,":[125],"as":[126,128],"well":[127],"its":[129],"superiority":[130],"other":[132],"works.":[133]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}