Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks
This addresses misinformation detection for web platforms, but appears incremental as it builds on existing adversarial attack and LLM methods.
The paper tackles adversarial misinformation attacks involving language-switching, translation, query inflation, and reformatting, presenting a multilingual multi-agent LLM framework with retrieval-augmented generation that can be deployed as a web plugin.
The rapid spread of misinformation on digital platforms threatens public discourse, emotional stability, and decision-making. While prior work has explored various adversarial attacks in misinformation detection, the specific transformations examined in this paper have not been systematically studied. In particular, we investigate language-switching across English, French, Spanish, Arabic, Hindi, and Chinese, followed by translation. We also study query length inflation preceding summarization and structural reformatting into multiple-choice questions. In this paper, we present a multilingual, multi-agent large language model framework with retrieval-augmented generation that can be deployed as a web plugin into online platforms. Our work underscores the importance of AI-driven misinformation detection in safeguarding online factual integrity against diverse attacks, while showcasing the feasibility of plugin-based deployment for real-world web applications.