{"id":"https://openalex.org/W3090447917","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206634","title":"Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence","display_name":"Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090447917","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206634","mag":"3090447917"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5020908862","display_name":"Yi Han","orcid":"https://orcid.org/0000-0001-6530-4564"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yi Han","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Parkville, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017066249","display_name":"David Hubczenko","orcid":null},"institutions":[{"id":"https://openalex.org/I1303474014","display_name":"Defence Science and Technology Group","ror":"https://ror.org/05ddrvt52","country_code":"AU","type":"government","lineage":["https://openalex.org/I1303474014","https://openalex.org/I2801453606","https://openalex.org/I3139952251"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Hubczenko","raw_affiliation_strings":["Australian Department of Defence Edinburgh, Defence Science and Technology Group, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Department of Defence Edinburgh, Defence Science and Technology Group, Australia","institution_ids":["https://openalex.org/I1303474014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024595046","display_name":"Paul Montague","orcid":"https://orcid.org/0000-0001-9461-7471"},"institutions":[{"id":"https://openalex.org/I1303474014","display_name":"Defence Science and Technology Group","ror":"https://ror.org/05ddrvt52","country_code":"AU","type":"government","lineage":["https://openalex.org/I1303474014","https://openalex.org/I2801453606","https://openalex.org/I3139952251"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Paul Montague","raw_affiliation_strings":["Australian Department of Defence Edinburgh, Defence Science and Technology Group, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Department of Defence Edinburgh, Defence Science and Technology Group, Australia","institution_ids":["https://openalex.org/I1303474014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026180696","display_name":"Olivier De Vel","orcid":"https://orcid.org/0000-0001-5179-3707"},"institutions":[{"id":"https://openalex.org/I1303474014","display_name":"Defence Science and Technology Group","ror":"https://ror.org/05ddrvt52","country_code":"AU","type":"government","lineage":["https://openalex.org/I1303474014","https://openalex.org/I2801453606","https://openalex.org/I3139952251"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Olivier De Vel","raw_affiliation_strings":["Australian Department of Defence Edinburgh, Defence Science and Technology Group, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Department of Defence Edinburgh, Defence Science and Technology Group, Australia","institution_ids":["https://openalex.org/I1303474014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077639290","display_name":"Tamas Abraham","orcid":"https://orcid.org/0000-0003-2466-7646"},"institutions":[{"id":"https://openalex.org/I1303474014","display_name":"Defence Science and Technology Group","ror":"https://ror.org/05ddrvt52","country_code":"AU","type":"government","lineage":["https://openalex.org/I1303474014","https://openalex.org/I2801453606","https://openalex.org/I3139952251"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tamas Abraham","raw_affiliation_strings":["Australian Department of Defence Edinburgh, Defence Science and Technology Group, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Department of Defence Edinburgh, Defence Science and Technology Group, Australia","institution_ids":["https://openalex.org/I1303474014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078824132","display_name":"Benjamin I. P. Rubinstein","orcid":"https://orcid.org/0000-0002-2947-6980"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Benjamin I. P. Rubinstein","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Parkville, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076014464","display_name":"Christopher Leckie","orcid":"https://orcid.org/0000-0002-4388-0517"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christopher Leckie","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Parkville, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060997326","display_name":"Tansu Alpcan","orcid":"https://orcid.org/0000-0002-7434-3239"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tansu Alpcan","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The University of Melbourne, Parkville, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070030398","display_name":"Sarah Erfani","orcid":"https://orcid.org/0000-0003-0885-0643"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sarah Erfani","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Parkville, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1354,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.56578919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9751999974250793,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.944100022315979,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.9402271509170532},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8525372743606567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7428740859031677},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6577604413032532},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5451676845550537},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47406190633773804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4648553133010864},{"id":"https://openalex.org/keywords/countermeasure","display_name":"Countermeasure","score":0.42251020669937134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3758552670478821},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13763204216957092}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9402271509170532},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8525372743606567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428740859031677},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6577604413032532},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5451676845550537},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47406190633773804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4648553133010864},{"id":"https://openalex.org/C21593369","wikidata":"https://www.wikidata.org/wiki/Q1032176","display_name":"Countermeasure","level":2,"score":0.42251020669937134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3758552670478821},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13763204216957092},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","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:10.1109/ijcnn48605.2020.9206634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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":54,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1564743226","https://openalex.org/W1673923490","https://openalex.org/W1932198206","https://openalex.org/W1945616565","https://openalex.org/W2041008854","https://openalex.org/W2095577883","https://openalex.org/W2112507308","https://openalex.org/W2125908420","https://openalex.org/W2155968351","https://openalex.org/W2180612164","https://openalex.org/W2201581102","https://openalex.org/W2243397390","https://openalex.org/W2408141691","https://openalex.org/W2543927648","https://openalex.org/W2603766943","https://openalex.org/W2604394466","https://openalex.org/W2746553466","https://openalex.org/W2763443044","https://openalex.org/W2773525213","https://openalex.org/W2773691349","https://openalex.org/W2803678876","https://openalex.org/W2803831897","https://openalex.org/W2883567023","https://openalex.org/W2887432790","https://openalex.org/W2941205169","https://openalex.org/W2949103145","https://openalex.org/W2962755762","https://openalex.org/W2963207607","https://openalex.org/W2963477884","https://openalex.org/W2963857521","https://openalex.org/W2964043796","https://openalex.org/W2964108292","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W2964283260","https://openalex.org/W2967595108","https://openalex.org/W3003546983","https://openalex.org/W3098276446","https://openalex.org/W4289752933","https://openalex.org/W4293846201","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6676935882","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6714069269","https://openalex.org/W6726114608","https://openalex.org/W6733049761","https://openalex.org/W6739868092","https://openalex.org/W6745326292","https://openalex.org/W6747027214","https://openalex.org/W6751569023","https://openalex.org/W6753570253"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3029572990"],"abstract_inverted_index":{"Recent":[0],"studies":[1,28],"have":[2],"demonstrated":[3,18],"that":[4,55,74,101,109,124],"reinforcement":[5,44],"learning":[6,22,45],"(RL)":[7],"agents":[8,81],"are":[9],"susceptible":[10],"to":[11,15,67,103,108,115],"adversarial":[12,118],"manipulation,":[13],"similar":[14],"vulnerabilities":[16],"previously":[17],"in":[19,31,46,143],"the":[20,29,32,57,61,68,76,84,91,105,125,130,133,140],"supervised":[21],"setting.":[23],"While":[24],"most":[25],"existing":[26],"work":[27],"problem":[30],"context":[33],"of":[34,90,132],"computer":[35],"vision":[36],"or":[37],"console":[38],"games,":[39],"this":[40],"paper":[41],"focuses":[42],"on":[43],"autonomous":[47],"cyber":[48],"defence":[49,99],"under":[50,56],"partial":[51,88],"observability.":[52],"We":[53],"demonstrate":[54],"black-box":[58],"setting,":[59],"where":[60],"attacker":[62,85,112],"has":[63,87],"no":[64],"direct":[65],"access":[66],"target":[69,75],"RL":[70,80],"model,":[71],"causative":[72,134],"attacks-attacks":[73],"training":[77,141],"process-can":[78],"poison":[79],"even":[82],"if":[83],"only":[86],"observability":[89],"environment.":[92],"In":[93],"addition,":[94],"we":[95],"propose":[96],"an":[97,111],"inversion":[98],"method":[100],"aims":[102],"apply":[104],"opposite":[106],"perturbation":[107],"which":[110],"might":[113],"use":[114],"generate":[116],"their":[117],"samples.":[119],"Our":[120],"experimental":[121],"results":[122],"illustrate":[123],"countermeasure":[126],"can":[127],"effectively":[128],"reduce":[129],"impact":[131],"attack,":[135],"while":[136],"not":[137],"significantly":[138],"affecting":[139],"process":[142],"non-attack":[144],"scenarios.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}