{"version":"1.0","type":"link","title":"Distillation attack - Newikis","description":"A distillation attack, also called adversarial distillation, illicit distillation or malicious distillation, is the training of a machine learning model, usually a large language model, on outputs collected from another developer's model in breach of that developer's terms of service or access…","provider_name":"Newikis","provider_url":"https://newikis.com","cache_age":86400}