Malak: AI-based multilingual personal assistant to combat misinformation and generative AI safety issues

TL;DR

Malak is a multilingual AI personal assistant designed to reduce misinformation and online harm, especially aiding users with lower digital literacy by providing user-friendly safety tools.

Contribution

This paper introduces Malak, a novel multilingual AI assistant aimed at combating misinformation and AI safety issues for users with varying digital literacy levels.

Findings

Malak effectively identifies and mitigates misinformation.

It enhances online safety for users with lower digital literacy.

The system demonstrates improved user engagement and safety awareness.

Abstract

The widespread use of AI technologies to generate digital content has led to increased misinformation and online harm. Deep fake technologies, a type of AI, make it easier to create convincing but fake content on social media, leading to various cyber threats. Malicious actors exploit AI capabilities, posing digital, physical, and psychological harm to individuals. While social media platforms have safety measures such as content rating and feedback systems, these are often used by people with higher digital literacy. There is a lack of preventive measures and a need for user-friendly tools that can be used by people with lower digital literacy. Our goal is to create a user-friendly multilingual AI-based personal assistant, Malak, to reduce online harm and promote safe online interactions, benefiting users with lower literacy levels.