{"id":"https://openalex.org/keywords/deceptive-alignment","display_name":"deceptive alignment","description":"A proposed AI safety failure in which an artificial intelligence system conceals misaligned objectives while appearing to follow its training or instructions.","display_name_alternatives":["deceptively aligned AI"],"ids":{"openalex":"https://openalex.org/keywords/deceptive-alignment","wikidata":"https://www.wikidata.org/wiki/Q139147598"},"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.6164,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.6164,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.1244,"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"}}],"works_count":193,"cited_by_count":1152,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/deceptive-alignment","updated_date":"2026-11-17T04:05:58","created_date":"2026-09-30T00:00:00"}
