Abstract
Large Language Model agents have begun to appear as personal assistants, customer service bots, and clinical aides. While these applications deliver substantial operational benefits, they also require continuous access to sensitive data, which increases the likelihood of unauthorized disclosures. This study proposes an auditing framework for conversational privacy that quantifies and audits these risks. The proposed Conversational Manipulation for Privacy Leakage (CMPL) framework, is an iterative probing strategy designed to stress-test agents that enforce strict privacy directives. Rather than focusing solely on a single disclosure event, CMPL simulates realistic multi-turn interactions to systematically uncover latent vulnerabilities. Our evaluation on diverse domains, data modalities, and safety configurations demonstrate the auditing framework’s ability to reveal privacy risks that are not deterred by existing single-turn defenses. In addition to introducing CMPL as a diagnostic tool, the paper delivers (1) an auditing procedure grounded in quantifiable risk metrics and (2) an open benchmark for evaluation of conversational privacy across agent implementations.
Saswat Das
PhD Student in Computer Science
My research interests include differential privacy, privacy-preserving machine learning (viz. DPML and Federated Learning), agentic LLMs, and cryptography.