{"id":"https://openalex.org/W2897573479","doi":"https://doi.org/10.1109/ijcnn.2018.8489741","title":"Adversarial Manipulation of Reinforcement Learning Policies in Autonomous Agents","display_name":"Adversarial Manipulation of Reinforcement Learning Policies in Autonomous Agents","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2897573479","doi":"https://doi.org/10.1109/ijcnn.2018.8489741","mag":"2897573479"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","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/A5103216219","display_name":"Yonghong Huang","orcid":"https://orcid.org/0000-0002-7706-5262"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yonghong Huang","raw_affiliation_strings":["McAfee LLC, Hillsboro, Oregon, USA"],"affiliations":[{"raw_affiliation_string":"McAfee LLC, Hillsboro, Oregon, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073176988","display_name":"Shih-Han Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shih-han Wang","raw_affiliation_strings":["Intel Corporation, Hillsboro, Oregon, USA"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Hillsboro, Oregon, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103216219"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8144,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79997108,"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":null,"last_page":null},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9878000020980835,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9377999901771545,"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/adversarial-system","display_name":"Adversarial system","score":0.9718348979949951},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8613897562026978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7155515551567078},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"Adversarial machine learning","score":0.7041287422180176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.641190230846405},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5670143365859985},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5133744478225708}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9718348979949951},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8613897562026978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7155515551567078},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.7041287422180176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.641190230846405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5670143365859985},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5133744478225708},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W9657784","https://openalex.org/W41554520","https://openalex.org/W769612788","https://openalex.org/W1574474448","https://openalex.org/W1673923490","https://openalex.org/W1771410628","https://openalex.org/W1945616565","https://openalex.org/W2095577883","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2151298633","https://openalex.org/W2165150801","https://openalex.org/W2180612164","https://openalex.org/W2243397390","https://openalex.org/W2257979135","https://openalex.org/W2258764094","https://openalex.org/W2462906003","https://openalex.org/W2528914598","https://openalex.org/W2530849036","https://openalex.org/W2535873859","https://openalex.org/W2583993537","https://openalex.org/W2616841723","https://openalex.org/W2759471388","https://openalex.org/W2774644650","https://openalex.org/W2941205169","https://openalex.org/W2949103145","https://openalex.org/W2962755762","https://openalex.org/W2963207607","https://openalex.org/W2963542245","https://openalex.org/W2963564844","https://openalex.org/W2963612069","https://openalex.org/W2963857521","https://openalex.org/W2963864421","https://openalex.org/W2963955657","https://openalex.org/W2964040467","https://openalex.org/W2964082701","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W3100944043","https://openalex.org/W4293529028","https://openalex.org/W4293846201","https://openalex.org/W4301501993","https://openalex.org/W4302570325","https://openalex.org/W6600428322","https://openalex.org/W6622262455","https://openalex.org/W6634423325","https://openalex.org/W6637162671","https://openalex.org/W6638018090","https://openalex.org/W6640425456","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6685943642","https://openalex.org/W6718836005","https://openalex.org/W6719080892","https://openalex.org/W6731685432","https://openalex.org/W6733049761","https://openalex.org/W6737897983","https://openalex.org/W6739868092","https://openalex.org/W6744511767","https://openalex.org/W6747220948"],"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/W2406556600","https://openalex.org/W4283221438","https://openalex.org/W2899811703"],"abstract_inverted_index":{"Machine":[0],"learning":[1,23,48,77],"classifiers":[2],"are":[3,17,42],"known":[4],"to":[5,8],"be":[6],"vulnerable":[7],"intentional":[9],"perturbation":[10],"of":[11,20,27,73,91,99,105,108],"inputs,":[12],"namely":[13],"adversarial":[14,21,40,65,83,111],"examples.":[15],"There":[16],"extensive":[18],"studies":[19],"machine":[22],"in":[24,45,55,103,110],"the":[25,63,74,89,92,97,100,106],"context":[26],"computer":[28],"vision":[29],"with":[30,85],"high":[31],"dimensional":[32],"inputs.":[33],"In":[34,79],"this":[35],"work,":[36],"we":[37,81,95],"show":[38,61],"that":[39,62],"attacks":[41],"also":[43],"effective":[44],"targeting":[46],"reinforcement":[47,76],"policies":[49],"based":[50],"on":[51,88],"low-dimensional":[52],"sensory":[53],"inputs":[54],"autonomous":[56],"agent":[57],"controls.":[58],"Our":[59],"results":[60],"two":[64],"example":[66],"crafting":[67],"techniques":[68],"significantly":[69],"degrade":[70],"test":[71],"performance":[72,109],"trained":[75],"policies.":[78],"addition,":[80],"compare":[82],"examples":[84],"random":[86],"noise":[87],"effectiveness":[90],"attacks.":[93,112],"Furthermore,":[94],"study":[96],"importance":[98],"input":[101],"features,":[102],"terms":[104],"impact":[107]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}