SAIF: A Comprehensive Framework for Evaluating the Risks of Generative AI in the Public Sector

TL;DR

This paper introduces SAIF, a comprehensive framework for systematically evaluating the risks of generative AI in the public sector, addressing the need for thorough risk assessment amidst its growing adoption.

Contribution

The paper presents SAIF, a novel systematic framework for evaluating and mitigating risks of multimodal generative AI in public sector applications.

Findings

SAIF enables comprehensive risk scenario generation.

It accommodates emerging jailbreak and prompt techniques.

Supports safer integration of AI in public services.

Abstract

The rapid adoption of generative AI in the public sector, encompassing diverse applications ranging from automated public assistance to welfare services and immigration processes, highlights its transformative potential while underscoring the pressing need for thorough risk assessments. Despite its growing presence, evaluations of risks associated with AI-driven systems in the public sector remain insufficiently explored. Building upon an established taxonomy of AI risks derived from diverse government policies and corporate guidelines, we investigate the critical risks posed by generative AI in the public sector while extending the scope to account for its multimodal capabilities. In addition, we propose a Systematic dAta generatIon Framework for evaluating the risks of generative AI (SAIF). SAIF involves four key stages: breaking down risks, designing scenarios, applying jailbreak methods, and exploring prompt types. It ensures the systematic and consistent generation of prompt data, facilitating a comprehensive evaluation while providing a solid foundation for mitigating the risks. Furthermore, SAIF is designed to accommodate emerging jailbreak methods and evolving prompt types, thereby enabling effective responses to unforeseen risk scenarios. We believe that this study can play a crucial role in fostering the safe and responsible integration of generative AI into the public sector.