{"id":"https://openalex.org/W4414079423","doi":"https://doi.org/10.1109/tsp.2025.3607114","title":"Human Feedback Attack on Online RLHF: Attack and Robust Defense","display_name":"Human Feedback Attack on Online RLHF: Attack and Robust Defense","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414079423","doi":"https://doi.org/10.1109/tsp.2025.3607114"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2025.3607114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2025.3607114","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-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/A5066891312","display_name":"Chenye Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenye Yang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA","Department of Electrical and Computer Engineering, University of California, Davis, CA"],"raw_orcid":"https://orcid.org/0009-0005-9273-3889","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, CA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mo Lyu","orcid":"https://orcid.org/0009-0003-3905-3142"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mo Lyu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA","Department of Electrical and Computer Engineering, University of California, Davis, CA"],"raw_orcid":"https://orcid.org/0009-0003-3905-3142","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, CA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073925794","display_name":"Guanlin Liu","orcid":"https://orcid.org/0000-0002-0595-9398"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanlin Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA","Department of Electrical and Computer Engineering, University of California, Davis, CA"],"raw_orcid":"https://orcid.org/0000-0002-0595-9398","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, CA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081715462","display_name":"Lifeng Lai","orcid":"https://orcid.org/0000-0002-9493-8248"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lifeng Lai","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA","Department of Electrical and Computer Engineering, University of California, Davis, CA"],"raw_orcid":"https://orcid.org/0000-0002-9493-8248","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, CA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":0.9389,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7969704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"73","issue":null,"first_page":"3886","last_page":"3901"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.980400025844574,"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"}},{"id":"https://openalex.org/T11498","display_name":"Security in Wireless Sensor Networks","score":0.9621000289916992,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.777400016784668},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.521399974822998},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5095999836921692},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.44369998574256897},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4275999963283539},{"id":"https://openalex.org/keywords/attack-model","display_name":"Attack model","score":0.38850000500679016}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.777400016784668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741100013256073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5095999836921692},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2980000078678131},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp.2025.3607114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2025.3607114","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8276422437","display_name":null,"funder_award_id":"CCF-2232907","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2763110165","https://openalex.org/W2794925984","https://openalex.org/W2951714068","https://openalex.org/W2962755762","https://openalex.org/W2975486888","https://openalex.org/W2981396729","https://openalex.org/W2997790181","https://openalex.org/W3007968297","https://openalex.org/W3145910327","https://openalex.org/W3203880515","https://openalex.org/W4212839863","https://openalex.org/W4213446860","https://openalex.org/W4226401482","https://openalex.org/W4388240411","https://openalex.org/W4389610366","https://openalex.org/W4393147287","https://openalex.org/W4393372876","https://openalex.org/W4403758821","https://openalex.org/W4410040027","https://openalex.org/W4411337824"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"human":[5],"feedback":[6],"attacks":[7],"on":[8],"online":[9,56,71],"Reinforcement":[10],"Learning":[11],"from":[12],"Human":[13],"Feedback":[14],"(RLHF)":[15],"algorithms.":[16],"The":[17,93],"attacker\u2019s":[18],"goal":[19],"is":[20,49,80,88],"to":[21,27,59,82],"force":[22],"the":[23,55,61,77],"victim":[24],"RLHF":[25,57,72],"algorithm":[26,58,79],"eventually":[28],"learn":[29,60],"a":[30,35,68,91],"suboptimal":[31,62],"policy":[32],"while":[33],"inducing":[34],"small":[36],"attack":[37,43,86],"cost.":[38],"We":[39,65,74],"propose":[40,67],"an":[41],"adversarial":[42],"strategy,":[44],"and":[45],"prove":[46],"that":[47,76],"it":[48],"successful":[50],"in":[51],"terms":[52],"of":[53],"misleading":[54],"target":[63],"policy.":[64],"also":[66],"robust":[69,81],"defense":[70],"algorithm.":[73],"show":[75],"proposed":[78],"any":[83],"attacker":[84],"whose":[85],"cost":[87],"bounded":[89],"by":[90],"budget.":[92],"simulation":[94],"results":[95],"validate":[96],"our":[97],"theoretical":[98],"analysis.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-08T23:21:52.890332","created_date":"2025-10-10T00:00:00"}
