Scholarlink

<p>Generative Artificial Intelligence (GenAI) has evolved into a transformative technology whose unprecedented growth and public exposure have revealed challenging issues ranging from privacy protection to reducing factual inaccuracies and hallucinations, model security risks, legal complications, and a lack of interpretability. This <i>position paper</i> examines how Differential Privacy (DP), a mathematical privacy protection framework, can address both privacy concerns <i>and</i> other systemic challenges beyond privacy in GenAI. We argue that DP is a versatile and underutilized tool with significant potential to address many critical GenAI issues. To argue our claim, we connect the core principle of DP to these issues, evaluate existing research, and pose relevant research questions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Beyond privacy: the potentialities of differential privacy in generative AI

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月19日

查看全文
  • Jonas Kuntzer,
  • Johannes Kaiser,
  • Tamara T. Mueller,
  • Anneliese Riess,
  • Kristian Schwethelm,
  • Georgios Kaissis,
  • Daniel Rueckert

摘要

Generative Artificial Intelligence (GenAI) has evolved into a transformative technology whose unprecedented growth and public exposure have revealed challenging issues ranging from privacy protection to reducing factual inaccuracies and hallucinations, model security risks, legal complications, and a lack of interpretability. This position paper examines how Differential Privacy (DP), a mathematical privacy protection framework, can address both privacy concerns and other systemic challenges beyond privacy in GenAI. We argue that DP is a versatile and underutilized tool with significant potential to address many critical GenAI issues. To argue our claim, we connect the core principle of DP to these issues, evaluate existing research, and pose relevant research questions.