paper-with-me

Papers

Operationalizing Contextual Integrity in Privacy-Conscious Assistants

2024-08-05 · Sahra Ghalebikesabi, Eugene Bagdasaryan, Ren Yi, Itay Yona, Ilia Shumailov, Aneesh Pappu, Chongyang Shi, Laura Weidinger, Robert Stanforth, Leonard Berrada, Pushmeet Kohli, Po-Sen Huang, Borja Balle

Advanced AI assistants combine frontier LLMs and tool access to autonomously perform complex tasks on behalf of users. While the helpfulness of such assistants can increase dramatically with access to user information including emails and documents, this raises privacy concerns about assistants sharing inappropriate information with third parties without user supervision. To steer information-sharing assistants to behave in accordance with privacy expectations, we propose to operationalize contextual integrity (CI), a framework that equates privacy with the appropriate flow of information in a given context. In particular, we design and evaluate a number of strategies to steer assistants' information-sharing actions to be CI compliant. Our evaluation is based on a novel form filling benchmark composed of human annotations of common webform applications, and it reveals that prompting frontier LLMs to perform CI-based reasoning yields strong results.

📄 PDF Abstract BibTeX arXiv:2408.02373

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation

2026-06-02 · Xinyue Huang, Xiaochun Cao, Wenyuan Yang arxiv

As LLMs become increasingly woven into everyday workflows, user queries sent to cloud hosted LLMs routinely mix task-essential content with task non-essential sensitive disclosures, yet type based PII redaction is contex…

Reinforcement Learning

MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Evaluation of Language Model Agents

2026-01-13 · Shouju Wang, Haopeng Zhang arxiv

As language-model agents evolve from passive chatbots into proactive assistants that handle personal data, evaluating their adherence to social norms becomes increasingly critical, often through the lens of Contextual In…

CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data

2024-09-20 · Zhao Cheng, Diane Wan, Matthew Abueg, Sahra Ghalebikesabi 외

Advances in generative AI point towards a new era of personalized applications that perform diverse tasks on behalf of users. While general AI assistants have yet to fully emerge, their potential to share personal data r…

BenchmarkingLanguage ModelingLanguage Modelling

AirGapAgent: Protecting Privacy-Conscious Conversational Agents

2024-05-08 · Eugene Bagdasarian, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz 외

The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns. While these agents excel at understanding and acting on context, this capabilit…

Language ModelingLanguage ModellingLarge Language Model

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

2023-10-27 · Niloofar Mireshghallah, Hyunwoo Kim, Xuhui Zhou, Yulia Tsvetkov 외

The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their …

Privacy Preserving