{"id":"https://openalex.org/W3197094019","doi":"https://doi.org/10.1109/menacomm50742.2021.9678308","title":"Segmentation Fault: A Cheap Defense Against Adversarial Machine Learning","display_name":"Segmentation Fault: A Cheap Defense Against Adversarial Machine Learning","publication_year":2021,"publication_date":"2021-12-03","ids":{"openalex":"https://openalex.org/W3197094019","doi":"https://doi.org/10.1109/menacomm50742.2021.9678308","mag":"3197094019"},"language":"en","primary_location":{"id":"doi:10.1109/menacomm50742.2021.9678308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/menacomm50742.2021.9678308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 3rd IEEE Middle East and North Africa COMMunications Conference (MENACOMM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5090702537","display_name":"Doha Al Bared","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Doha Al Bared","raw_affiliation_strings":["American University of Beirut (AUB), Beirut, Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University of Beirut (AUB), Beirut, Lebanon","institution_ids":["https://openalex.org/I98635879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043344581","display_name":"Mohamed Nassar","orcid":"https://orcid.org/0000-0001-8857-4436"},"institutions":[{"id":"https://openalex.org/I40253897","display_name":"University of New Haven","ror":"https://ror.org/00zm4rq24","country_code":"US","type":"education","lineage":["https://openalex.org/I40253897"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Nassar","raw_affiliation_strings":["University of New Haven, West Haven, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Haven, West Haven, CT, USA","institution_ids":["https://openalex.org/I40253897"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":1.0,"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":1.0,"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/T11515","display_name":"Bacillus and Francisella bacterial research","score":0.9621000289916992,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9498999714851379,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8047254681587219},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7548872232437134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7348065972328186},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6626387238502502},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6211071610450745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6050440073013306},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.570198118686676},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5395658612251282},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4961620271205902},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4858643412590027},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4548833668231964},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41179654002189636},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37363141775131226},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15707126259803772},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09349846839904785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047254681587219},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7548872232437134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7348065972328186},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6626387238502502},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6211071610450745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6050440073013306},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.570198118686676},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5395658612251282},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4961620271205902},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4858643412590027},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4548833668231964},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41179654002189636},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37363141775131226},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15707126259803772},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09349846839904785},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/menacomm50742.2021.9678308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/menacomm50742.2021.9678308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 3rd IEEE Middle East and North Africa COMMunications Conference (MENACOMM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1508404128","https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W1999478155","https://openalex.org/W2015159529","https://openalex.org/W2118246710","https://openalex.org/W2243397390","https://openalex.org/W2603766943","https://openalex.org/W2607219512","https://openalex.org/W2736899637","https://openalex.org/W2765424254","https://openalex.org/W2945374319","https://openalex.org/W2963070423","https://openalex.org/W2963389226","https://openalex.org/W2963857521","https://openalex.org/W2964082701","https://openalex.org/W2998600476","https://openalex.org/W3011659198","https://openalex.org/W3088909400","https://openalex.org/W3103557498","https://openalex.org/W3118608800","https://openalex.org/W3120349939","https://openalex.org/W4247200422","https://openalex.org/W4293846201","https://openalex.org/W4394663350","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6729756640","https://openalex.org/W6736207377","https://openalex.org/W6739868092","https://openalex.org/W6741036071","https://openalex.org/W6746608116","https://openalex.org/W6787972765","https://openalex.org/W6864274290"],"related_works":["https://openalex.org/W3176659669","https://openalex.org/W4287115361","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2950183588","https://openalex.org/W3080754722","https://openalex.org/W4383221314","https://openalex.org/W2951211570","https://openalex.org/W3103566983"],"abstract_inverted_index":{"Recently":[0],"published":[1,98],"attacks":[2],"against":[3],"deep":[4,43,59],"neural":[5,60],"networks":[6],"(DNNs)":[7],"have":[8],"stressed":[9],"the":[10,18,40,73,104,121],"importance":[11],"of":[12,21,42,89,111,123],"methodologies":[13],"and":[14,38,47,63,119],"tools":[15],"to":[16,85,95],"assess":[17],"security":[19,48],"risks":[20],"using":[22],"this":[23,50,128],"technology":[24],"in":[25,45,66,72,87,137,148],"critical":[26],"systems.":[27],"Efficient":[28],"techniques":[29],"for":[30,57,127],"detecting":[31],"adversarial":[32],"machine":[33],"learning":[34,44],"helps":[35],"establishing":[36],"trust":[37],"boost":[39],"adoption":[41],"sensitive":[46],"systems.In":[49],"paper,":[51],"we":[52],"propose":[53],"a":[54,82,96,134,145],"new":[55],"technique":[56,99],"defending":[58],"network":[61],"classifiers,":[62],"convolutional":[64],"ones":[65],"particular.":[67],"Our":[68,130],"defense":[69],"is":[70,139],"cheap":[71],"sense":[74],"that":[75,133],"it":[76],"requires":[77],"less":[78],"computation":[79],"power":[80],"despite":[81],"small":[83],"cost":[84],"pay":[86],"terms":[88],"detection":[90,149],"accuracy.":[91,150],"The":[92],"work":[93],"refers":[94],"recently":[97],"called":[100],"ML-LOO.":[101],"We":[102,117],"replace":[103],"costly":[105],"pixel":[106,108],"by":[107,113,144],"leave-one-out":[109],"approach":[110],"ML-LOO":[112],"adopting":[114],"coarse-grained":[115],"leave-one-out.":[116],"evaluate":[118],"compare":[120],"efficiency":[122,138],"different":[124],"segmentation":[125],"algorithms":[126],"task.":[129],"results":[131],"show":[132],"large":[135],"gain":[136],"possible,":[140],"even":[141],"though":[142],"penalized":[143],"marginal":[146],"decrease":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}