{"id":"https://openalex.org/W2899111971","doi":"https://doi.org/10.23919/date.2019.8715141","title":"FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning","display_name":"FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2899111971","doi":"https://doi.org/10.23919/date.2019.8715141","mag":"2899111971"},"language":"en","primary_location":{"id":"doi:10.23919/date.2019.8715141","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8715141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5074265316","display_name":"Faiq Khalid","orcid":"https://orcid.org/0000-0001-6263-674X"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Faiq Khalid","raw_affiliation_strings":["Vienna University of Technology, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100647460","display_name":"Muhammad Abdullah Hanif","orcid":"https://orcid.org/0000-0001-9841-6132"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Muhammad Abdullah Hanif","raw_affiliation_strings":["Vienna University of Technology, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058712739","display_name":"Semeen Rehman","orcid":"https://orcid.org/0000-0002-8972-0949"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Semeen Rehman","raw_affiliation_strings":["Vienna University of Technology, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037574053","display_name":"Junaid Qadir","orcid":"https://orcid.org/0000-0001-9466-2475"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Junaid Qadir","raw_affiliation_strings":["Information Technology University, Lahore, Pakistan"],"affiliations":[{"raw_affiliation_string":"Information Technology University, Lahore, Pakistan","institution_ids":["https://openalex.org/I1323252656"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005190949","display_name":"Muhammad Shafique","orcid":"https://orcid.org/0000-0002-2607-8135"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Muhammad Shafique","raw_affiliation_strings":["Vienna University of Technology, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074265316"],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":3.3604,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.93856644,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"902","last_page":"907"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9699000120162964,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9491000175476074,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.829259991645813},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"Adversarial machine learning","score":0.820141077041626},{"id":"https://openalex.org/keywords/traffic-sign-recognition","display_name":"Traffic sign recognition","score":0.7850794792175293},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7664709091186523},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6738690137863159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6477392315864563},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6151063442230225},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6105323433876038},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.592793881893158},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5217676758766174},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48390159010887146},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4680958092212677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4590974450111389},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42102333903312683},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3288351893424988},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22093987464904785},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16030117869377136},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.1194598376750946},{"id":"https://openalex.org/keywords/traffic-sign","display_name":"Traffic sign","score":0.11501526832580566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829259991645813},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.820141077041626},{"id":"https://openalex.org/C6528762","wikidata":"https://www.wikidata.org/wiki/Q1574298","display_name":"Traffic sign recognition","level":4,"score":0.7850794792175293},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7664709091186523},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6738690137863159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6477392315864563},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6151063442230225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6105323433876038},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.592793881893158},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5217676758766174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48390159010887146},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4680958092212677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4590974450111389},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42102333903312683},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3288351893424988},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22093987464904785},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16030117869377136},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.1194598376750946},{"id":"https://openalex.org/C2983860417","wikidata":"https://www.wikidata.org/wiki/Q170285","display_name":"Traffic sign","level":3,"score":0.11501526832580566},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date.2019.8715141","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8715141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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":48,"referenced_works":["https://openalex.org/W9657784","https://openalex.org/W1673923490","https://openalex.org/W1932198206","https://openalex.org/W1945616565","https://openalex.org/W2117876524","https://openalex.org/W2151298633","https://openalex.org/W2180612164","https://openalex.org/W2216949779","https://openalex.org/W2528914598","https://openalex.org/W2535690855","https://openalex.org/W2572504188","https://openalex.org/W2603766943","https://openalex.org/W2607219512","https://openalex.org/W2746600820","https://openalex.org/W2785405530","https://openalex.org/W2787816497","https://openalex.org/W2788963265","https://openalex.org/W2789959313","https://openalex.org/W2798919674","https://openalex.org/W2809895662","https://openalex.org/W2888975495","https://openalex.org/W2962763344","https://openalex.org/W2963003451","https://openalex.org/W2963070423","https://openalex.org/W2963098487","https://openalex.org/W2963744840","https://openalex.org/W2963857521","https://openalex.org/W3103557498","https://openalex.org/W3103836116","https://openalex.org/W3106412272","https://openalex.org/W4211047985","https://openalex.org/W4211122380","https://openalex.org/W4247200422","https://openalex.org/W4298140072","https://openalex.org/W4300511536","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6688365552","https://openalex.org/W6719080892","https://openalex.org/W6736207377","https://openalex.org/W6738693630","https://openalex.org/W6746608116","https://openalex.org/W6748302153","https://openalex.org/W6748526662","https://openalex.org/W6748777904","https://openalex.org/W6750462152","https://openalex.org/W6754272107","https://openalex.org/W6785841629"],"related_works":["https://openalex.org/W3048732067","https://openalex.org/W4383468834","https://openalex.org/W4384648009","https://openalex.org/W4303645823","https://openalex.org/W4285263558","https://openalex.org/W2900159906","https://openalex.org/W4287828318","https://openalex.org/W2950183588","https://openalex.org/W2406556600","https://openalex.org/W4293054861"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNN)-based":[3],"machine":[4],"learning":[5,28],"(ML)":[6],"algorithms":[7],"have":[8],"recently":[9],"emerged":[10],"as":[11,42],"the":[12,18,51,59,63,89,98,104,110,119,126,150,153,169,172,188,191,202,207,229],"leading":[13],"ML":[14,69,182],"paradigm":[15],"particularly":[16],"for":[17,118,206],"task":[19],"of":[20,27,35,38,53,65,109,152,171,190,231],"classification":[21],"due":[22],"to":[23,80,135,225],"their":[24],"superior":[25],"capability":[26],"efficiently":[29],"from":[30,164],"large":[31],"dataseis.":[32],"The":[33],"discovery":[34],"a":[36,86,140,176,223],"number":[37],"well-known":[39,78],"attacks":[40,79,113],"such":[41],"dataset":[43],"poisoning,":[44],"adversarial":[45,112,161,197],"examples,":[46],"and":[47],"network":[48],"manipulation":[49],"(through":[50],"addition":[52],"malicious":[54,73],"nodes)":[55],"has,":[56],"however,":[57,115],"put":[58],"spotlight":[60],"squarely":[61],"on":[62,159],"lack":[64],"security":[66],"in":[67,88,131,228],"DNN-based":[68],"systems.":[70],"In":[71],"particular,":[72],"actors":[74],"can":[75,147,221],"use":[76],"these":[77,144],"cause":[81,85,222],"random/targeted":[82],"misclassification,":[83],"or":[84,103],"change":[87],"prediction":[90],"confidence,":[91],"by":[92,174,200],"only":[93],"slightly":[94],"but":[95],"systematically":[96],"manipulating":[97],"environmental":[99],"parameters,":[100],"inference":[101],"data,":[102],"data":[105],"acquisition":[106],"block.":[107],"Most":[108],"prior":[111],"have,":[114],"not":[116],"accounted":[117],"pre-processing":[120,178],"noise":[121,145,179,233],"filters":[122,146],"commonly":[123],"integrated":[124],"with":[125],"ML-inference":[127],"module.":[128],"Our":[129],"contribution":[130],"this":[132,138],"work":[133],"is":[134,139],"show":[136],"that":[137],"major":[141],"omission":[142],"since":[143],"render":[148],"ineffective":[149],"majority":[151],"existing":[154],"attacks,":[155],"which":[156,215],"rely":[157],"essentially":[158],"introducing":[160],"noise.":[162],"Apart":[163],"this,":[165],"we":[166,194],"also":[167],"extend":[168],"state":[170],"art":[173],"proposing":[175],"novel":[177],"Filter-aware":[180],"Adversarial":[181],"attack":[183,198],"called":[184],"FAdeML.":[185],"To":[186],"demonstrate":[187],"effectiveness":[189],"proposed":[192],"methodology,":[193],"generate":[195],"an":[196],"image":[199],"exploiting":[201],"\"VGGNet\"":[203],"DNN":[204],"trained":[205],"\"German":[208],"Traffic":[209],"Sign":[210],"Recognition":[211],"Benchmarks":[212],"(GTSRB)\"":[213],"dataset,":[214],"despite":[216],"having":[217],"no":[218],"visual":[219],"noise,":[220],"classifier":[224],"misclassify":[226],"even":[227],"presence":[230],"preprocessing":[232],"filters.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}