Operationalizing Contextual Integrity in Privacy-Conscious Assistants
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909314273247232 |
|---|---|
| author | Ghalebikesabi, Sahra Bagdasaryan, Eugene Yi, Ren Yona, Itay Shumailov, Ilia Pappu, Aneesh Shi, Chongyang Weidinger, Laura Stanforth, Robert Berrada, Leonard Kohli, Pushmeet Huang, Po-Sen Balle, Borja |
| author_facet | Ghalebikesabi, Sahra Bagdasaryan, Eugene Yi, Ren Yona, Itay Shumailov, Ilia Pappu, Aneesh Shi, Chongyang Weidinger, Laura Stanforth, Robert Berrada, Leonard Kohli, Pushmeet Huang, Po-Sen Balle, Borja |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02373 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Operationalizing Contextual Integrity in Privacy-Conscious Assistants Ghalebikesabi, Sahra Bagdasaryan, Eugene Yi, Ren Yona, Itay Shumailov, Ilia Pappu, Aneesh Shi, Chongyang Weidinger, Laura Stanforth, Robert Berrada, Leonard Kohli, Pushmeet Huang, Po-Sen Balle, Borja Artificial Intelligence 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. |
| title | Operationalizing Contextual Integrity in Privacy-Conscious Assistants |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2408.02373 |