PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization

Abstract

Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information (PII) from public pages. Many prior defenses are deployed at the model, service, or agent layer rather than at the webpage itself, leaving ordinary page owners with limited deployable options. We present PIIGuard, a webpage-level defense that repurposes indirect prompt injection as a protective mechanism: the page owner

Categories

Framework mappings

Suggested from the entry's categories.

@misc{liu2026piiguard,
  title = {{PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization}},
  author = {Mingshuo Liu and Yiwei Zha and Min Chen},
  year = {2026},
  month = may,
  eprint = {2605.03129},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.03129}
}