Privacy Reasoning in Ambiguous Contexts

Ren Yi, Octavian Suciu, Adrian Gascon, Sarah Meiklejohn, Eugene Bagdasarian, Marco Gruteser

Keywords: Personal Agents, Privacy Reasoning, Context Disambiguation, Benchmarks

TL;DR: Context ambiguity hinders privacy assessment performance of frontier and reasoning LLMs. Disambiguating contexts based on the reasoning models provide significantly improves their privacy judgements and reduces their sensitivity to prompts.

Abstract: We study the ability of language models to reason about appropriate information disclosure - a central aspect of the evolving field of agentic privacy. Whereas previous works have focused on evaluating a model's ability to align with human decisions, we examine the role of ambiguity and missing context on model performance when making information-sharing decisions. We identify context ambiguity as a crucial barrier for high performance in privacy assessments. By designing Camber, a framework for context disambiguation, we show that model-generated decision rationales can reveal ambiguities and that systematically disambiguating context based on these rationales leads to significant accuracy improvements (up to 13.3% in precision and up to 22.3% in recall) as well as reductions in prompt sensitivity. Overall, our results indicate that approaches for context disambiguation are a promising way forward to enhance agentic privacy reasoning.

Primary Area: Social and economic aspects of machine learning (e.g., fairness, interpretability, human-AI interaction, privacy, safety, strategic behavior)

Submission Number: 13727