PII-Bench: Evaluating Query-Aware Privacy Protection Systems

Research Summary

Contribution Summary

• The widespread adoption of Large Language Models (LLMs) has raised significant privacy concerns regarding the exposure of personally identifiable information (PII) in user prompts.
• To address this challenge, we propose a query-unrelated PII masking strategy and introduce PII-Bench, the first comprehensive evaluation framework for assessing privacy protection systems.
• PII-Bench comprises 2,842 test samples across 55 fine-grained PII categories, featuring diverse scenarios from single-subject descriptions to complex multi-party interactions.

Why It Matters For Eval

• To address this challenge, we propose a query-unrelated PII masking strategy and introduce PII-Bench, the first comprehensive evaluation framework for assessing privacy protection systems.
• Our empirical evaluation reveals that while current models perform adequately in basic PII detection, they show significant limitations in determining PII query relevance.

Related Papers

• Supercharging Agenda Setting Research: The ParlaCAP Dataset of 28 European Parliaments and a Scalable Multilingual LLM-Based Classification Embedding Neighbor
• Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence Embedding Neighbor
• Variable-Length Semantic IDs for Recommender Systems Embedding Neighbor
• One Brain, Omni Modalities: Towards Unified Non-Invasive Brain Decoding with Large Language Models Embedding Neighbor
• Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study Embedding Neighbor
• Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models Embedding Neighbor
• Continuous Telemonitoring of Heart Failure using Personalised Speech Dynamics Embedding Neighbor
• DistillNote: Toward a Functional Evaluation Framework of LLM-Generated Clinical Note Summaries Embedding Neighbor
• RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments Embedding Neighbor
• The Headless Firm: How AI Reshapes Enterprise Boundaries Tag Overlap
• Measuring AI Ability to Complete Long Software Tasks Tag Overlap
• Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers Tag Overlap