{"id":"https://openalex.org/W3011713982","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023341","title":"Filtering Adversarial Noise with Double Quantization","display_name":"Filtering Adversarial Noise with Double Quantization","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011713982","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023341","mag":"3011713982"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5061499776","display_name":"AprilPyone MaungMaung","orcid":"https://orcid.org/0000-0002-0036-6577"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"MaungMaung AprilPyone","raw_affiliation_strings":["Tokyo Metropolitan University, Asahigaoka, Hino-shi, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Asahigaoka, Hino-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043769131","display_name":"Yuma Kinoshita","orcid":"https://orcid.org/0000-0001-8455-1288"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Kinoshita","raw_affiliation_strings":["Tokyo Metropolitan University, Asahigaoka, Hino-shi, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Asahigaoka, Hino-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015250468","display_name":"Hitoshi Kiya","orcid":"https://orcid.org/0000-0001-8061-3090"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Kiya","raw_affiliation_strings":["Tokyo Metropolitan University, Asahigaoka, Hino-shi, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Asahigaoka, Hino-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061499776"],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60591291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"17","issue":null,"first_page":"1745","last_page":"1749"},"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11515","display_name":"Bacillus and Francisella bacterial research","score":0.9430999755859375,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.9520880579948425},{"id":"https://openalex.org/keywords/dither","display_name":"Dither","score":0.9272594451904297},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7006628513336182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6792514324188232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5389121174812317},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4593333303928375},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.4243318438529968},{"id":"https://openalex.org/keywords/noise-shaping","display_name":"Noise shaping","score":0.23242905735969543},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15998771786689758}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9520880579948425},{"id":"https://openalex.org/C70451592","wikidata":"https://www.wikidata.org/wiki/Q376493","display_name":"Dither","level":3,"score":0.9272594451904297},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7006628513336182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6792514324188232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5389121174812317},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4593333303928375},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.4243318438529968},{"id":"https://openalex.org/C9083635","wikidata":"https://www.wikidata.org/wiki/Q2133535","display_name":"Noise shaping","level":2,"score":0.23242905735969543},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15998771786689758},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":28,"referenced_works":["https://openalex.org/W9657784","https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W2194775991","https://openalex.org/W2408141691","https://openalex.org/W2517229335","https://openalex.org/W2603766943","https://openalex.org/W2919115771","https://openalex.org/W2963389226","https://openalex.org/W2963857521","https://openalex.org/W2963969878","https://openalex.org/W2964082701","https://openalex.org/W2964153729","https://openalex.org/W2983044655","https://openalex.org/W3010086541","https://openalex.org/W3103836116","https://openalex.org/W3118608800","https://openalex.org/W4293846201","https://openalex.org/W4300511536","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6714069269","https://openalex.org/W6719080892","https://openalex.org/W6726407388","https://openalex.org/W6729756640","https://openalex.org/W6739868092","https://openalex.org/W6752654261","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4320018150","https://openalex.org/W2040808657","https://openalex.org/W4239582170","https://openalex.org/W2094272778","https://openalex.org/W2918664383","https://openalex.org/W2000868246","https://openalex.org/W4210717739","https://openalex.org/W106056076","https://openalex.org/W4320855730","https://openalex.org/W2135200719"],"abstract_inverted_index":{"Despite":[0],"deep":[1,23],"learning":[2],"being":[3],"powerful":[4],"to":[5,46,55,138],"solve":[6],"challenging":[7],"problems,":[8],"it":[9],"is":[10,160,167],"vulnerable":[11],"towards":[12],"adversarial":[13,18,32,63,82,127,144,153],"examples.":[14,64],"To":[15],"defend":[16],"these":[17],"blind":[19],"spots":[20],"in":[21,50,101],"the":[22,36,66,88,109,130,148,156,165],"learning,":[24],"researchers":[25],"have":[26],"proposed":[27,67,89,110,149],"various":[28],"approaches.":[29],"However,":[30],"conventional":[31],"training":[33,52,72],"can":[34,151],"reduce":[35],"accuracy":[37,58,116,141],"significantly.":[38],"In":[39,135],"this":[40],"paper,":[41],"we":[42],"propose":[43],"a":[44,79,92],"method":[45,68,90,111,150],"incorporate":[47],"quantized":[48],"images":[49],"both":[51,60,124,143],"and":[53,62,73,75,97,114,119,126,145],"testing":[54],"maintain":[56],"identical":[57,140],"for":[59,117,123,142,164],"normal":[61,125,146],"Specifically,":[65],"utilizes":[69],"dithering":[70,74],"during":[71,84],"linear":[76],"quantization":[77],"as":[78],"mean":[80],"of":[81,133],"filtering":[83],"testing.":[85],"We":[86],"evaluated":[87],"with":[91],"well-known":[93],"strong":[94],"first-order":[95],"adversary":[96],"also":[98],"conducted":[99],"experiments":[100,166],"different":[102],"bit":[103],"depths.":[104],"The":[105,162],"results":[106],"suggest":[107],"that":[108],"achieves":[112],"87.14%":[113],"85.28%":[115],"2-bit":[118],"1-bit":[120],"dithered":[121],"models":[122],"tests":[128],"on":[129,169],"noise":[131],"level":[132],"8.":[134],"addition,":[136],"due":[137],"having":[139],"tests,":[147],"detect":[152],"examples":[154],"if":[155],"original":[157],"test":[158],"dataset":[159],"known.":[161],"code":[163],"released":[168],"https://github.com/fugokidi/one-bit-quantization.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}