{"id":"https://openalex.org/W7127973153","doi":"https://doi.org/10.48550/arxiv.2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","display_name":"Position: Capability Control Should be a Separate Goal From Alignment","publication_year":2026,"publication_date":"2026-02-05","ids":{"openalex":"https://openalex.org/W7127973153","doi":"https://doi.org/10.48550/arxiv.2602.05164"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.05164","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053635416","display_name":"Shoaib Ahmed Siddiqui","orcid":"https://orcid.org/0000-0003-4600-7331"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Siddiqui, Shoaib Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125202483","display_name":"Eleni Triantafillou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Triantafillou, Eleni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125164017","display_name":"David Krueger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krueger, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042278493","display_name":"Adrian Weller","orcid":"https://orcid.org/0000-0003-1915-7158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weller, Adrian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053635416"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9297999739646912,"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":0.9297999739646912,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.01140000019222498,"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/T11424","display_name":"Security and Verification in Computing","score":0.00860000029206276,"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/control","display_name":"Control (management)","score":0.6532999873161316},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6430000066757202},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5874999761581421},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5866000056266785},{"id":"https://openalex.org/keywords/position-paper","display_name":"Position paper","score":0.4244999885559082},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.35920000076293945},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.35370001196861267}],"concepts":[{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6532999873161316},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6430000066757202},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.576200008392334},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.374099999666214},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C92991967","wikidata":"https://www.wikidata.org/wiki/Q7644329","display_name":"Supervisory control","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.27309998869895935},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.05164","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.05164","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05164","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.05164","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Foundation":[0],"models":[1],"are":[2],"trained":[3],"on":[4,36,65],"broad":[5],"data":[6],"distributions,":[7],"yielding":[8],"generalist":[9],"capabilities":[10],"that":[11,30,128],"enable":[12],"many":[13],"downstream":[14],"applications":[15],"but":[16],"also":[17],"expand":[18],"the":[19,78,88,133,147],"space":[20],"of":[21,87,150],"potential":[22],"misuse":[23],"and":[24,55,99,109,152],"failures.":[25],"This":[26],"position":[27],"paper":[28],"argues":[29],"capability":[31,57,74],"control":[32,58,75,86,93,102],"--":[33,40],"imposing":[34],"restrictions":[35],"permissible":[37,66],"model":[38,79],"behavior":[39],"should":[41],"be":[42],"treated":[43],"as":[44],"a":[45,125],"distinct":[46],"goal":[47],"from":[48],"alignment.":[49],"While":[50],"alignment":[51],"is":[52],"often":[53],"context":[54],"preference-driven,":[56],"aims":[59],"to":[60],"impose":[61],"hard":[62],"operational":[63],"limits":[64],"behaviors,":[67],"including":[68,146],"under":[69],"adversarial":[70],"elicitation.":[71],"We":[72,136],"organize":[73],"mechanisms":[76],"across":[77,132],"lifecycle":[80],"into":[81],"three":[82],"layers:":[83],"(i)":[84],"data-based":[85],"training":[89],"distribution,":[90],"(ii)":[91],"learning-based":[92],"via":[94,103],"weight-":[95],"or":[96],"representation-level":[97],"interventions,":[98],"(iii)":[100],"system-based":[101],"post-deployment":[104],"guardrails":[105],"over":[106],"inputs,":[107],"outputs,":[108],"actions.":[110],"Because":[111],"each":[112],"layer":[113],"has":[114],"characteristic":[115],"failure":[116],"modes":[117],"when":[118],"used":[119],"in":[120,142],"isolation,":[121],"we":[122],"advocate":[123],"for":[124],"defense-in-depth":[126],"approach":[127],"composes":[129],"complementary":[130],"controls":[131],"full":[134],"stack.":[135],"further":[137],"outline":[138],"key":[139],"open":[140],"challenges":[141],"achieving":[143],"such":[144],"control,":[145],"dual-use":[148],"nature":[149],"knowledge":[151],"compositional":[153],"generalization.":[154]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-02-07T00:00:00"}
