Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions
Vol. 17, Issue 6 (2026)The increasing adoption of large language mod-els (LLMs) and domain-adapted transformers in healthcare has created a new privacy challenge: fine-tuned models may memorize rare clinical strings and later reveal them throu…