Work

Toward Trustworthy Artificial Intelligence: An Integrated Framework Approach Mitigating Threats

Year: 2024

Type: article

Abstract: We present the Strategic Artificial Intelligence (AI) Threats Navigation matrix, an integrated approach to navigating AI threats and trustworthiness throughout the AI lifecycle. It aims to assist developers, data scientists, regulators, and users in addressing threats and bolstering AI’s reliability, encouraging an improvement of trustworthiness.

Source: Computer

DOI: 10.1109/mc.2024.3400532

Authors: Kíng-Pîng Tēnn, Yu-Wei Chang, Hong-Yen Chen, Teng-Kai Fan, Tsungnan Lin

Institutions: National Taiwan University, Chunghwa Telecom (Taiwan)

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Safety Research

Field: Social Sciences

Domain: Social Sciences

Open Access status: hybrid

Estimated APC paid: $2,995

Funders: National Science Council, Chunghwa Telecom Laboratories