Researchers have developed PIIGuard, a novel webpage-level defense system designed to prevent large language models (LLMs) from harvesting personally identifiable information (PII). This system embeds hidden HTML fragments within webpages that subtly redirect LLMs away from disclosing sensitive data. PIIGuard demonstrated a defense success rate of at least 97.0% across several LLM models, including GPT-5.4-nano, Claude-haiku-4.5, and DeepSeek-chat, while maintaining the page's utility for standard question-answering tasks. AI
影响 Offers a new method for website owners to protect user data from LLM-based scraping.
排序理由 Academic paper detailing a new method for mitigating PII leakage from LLMs.
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
