{"id":"https://openalex.org/keywords/jailbreak-detection","display_name":"jailbreak detection","description":"Techniques for identifying inputs or interactions intended to bypass safety restrictions in large language models.","display_name_alternatives":["LLM jailbreak detection","jailbreaking detection","detection of jailbreak attempts","large language model jailbreak detection"],"ids":{"openalex":"https://openalex.org/keywords/jailbreak-detection","wikidata":null},"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8162,"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":0.8162,"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":185,"cited_by_count":2246,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/jailbreak-detection","updated_date":"2026-11-21T04:06:33","created_date":"2026-09-30T00:00:00"}
