PIIGuard uses optimized hidden HTML fragments on webpages to block LLMs from leaking contact PII via indirect prompt injection, achieving at least 97% defense success across tested models while preserving benign QA utility.
Automated privacy information annotation in large language model interactions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
LLMs support taxonomy-agnostic detection and value extraction of PII in HTTP traffic via a deterministic pre-processing plus classification pipeline, plus an LLM generator for synthetic labeled traffic.
citing papers explorer
-
PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization
PIIGuard uses optimized hidden HTML fragments on webpages to block LLMs from leaking contact PII via indirect prompt injection, achieving at least 97% defense success across tested models while preserving benign QA utility.