paper-with-me

Papers

Disclosure Audits for LLM Agents

2025-06-11 · Saswat Das, Jameson Sandler, Ferdinando Fioretto

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.

📄 PDF Abstract BibTeX arXiv:2506.10171

Code (0)

등록된 구현이 없습니다.

Tasks

DiagnosticLanguage ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

2026-06-26 · Shijing Hu, Liang Liu, Zhu Meng, Zhicheng Zhao arxiv

Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks. However, conventional function-calling…

Text Generation

C3PA: An Open Dataset of Expert-Annotated and Regulation-Aware Privacy Policies to Enable Scalable Regulatory Compliance Audits

2024-10-04 · Maaz Bin Musa, Steven M. Winston, Garrison Allen, Jacob Schiller 외

The development of tools and techniques to analyze and extract organizations data habits from privacy policies are critical for scalable regulatory compliance audits. Unfortunately, these tools are becoming increasingly …

Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits

2026-07-01 · Yanhang Li, Zhichao Fan, Zexin Zhuang arxiv

Governance frameworks ask AI providers and auditors for documented evaluation evidence, and perturbation-based construct-validity audits are a common form of that evidence. We argue the audits are themselves fragile: the…

Fairness Auditing with Multi-Agent Collaboration

2024-02-13 · Martijn de Vos, Akash Dhasade, Jade Garcia Bourrée, Anne-Marie Kermarrec 외

Existing work in fairness auditing assumes that each audit is performed independently. In this paper, we consider multiple agents working together, each auditing the same platform for different tasks. Agents have two lev…

Decision MakingFairness

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent

2025-02-18 · Pengyu Zhu, Zhenhong Zhou, Yuanhe Zhang, Shilinlu Yan 외

As LLM-based agents become increasingly prevalent, backdoors can be implanted into agents through user queries or environment feedback, raising critical concerns regarding safety vulnerabilities. However, backdoor attack…