Building Resilient Information Ecosystems: Large LLM-Generated Dataset of Persuasion Attacks

TL;DR

This paper introduces a large dataset of over 134,000 persuasion attacks generated by advanced language models to study and improve the resilience of organizational communication against AI-driven misinformation.

Contribution

It presents a novel, large-scale dataset of LLM-generated persuasion attacks across multiple models and communication mediums, enabling proactive defense strategies.

Findings

GPT-4 attacks focus on Care, Authority, and Loyalty.

Gemma 2 emphasizes Care and Authority.

Llama 3.1 centers on Loyalty and Care.

Abstract

Organization's communication is essential for public trust, but the rise of generative AI models has introduced significant challenges by generating persuasive content that can form competing narratives with official messages from government and commercial organizations at speed and scale. This has left agencies in a reactive position, often unaware of how these models construct their persuasive strategies, making it more difficult to sustain communication effectiveness. In this paper, we introduce a large LLM-generated persuasion attack dataset, which includes 134,136 attacks generated by GPT-4, Gemma 2, and Llama 3.1 on agency news. These attacks span 23 persuasive techniques from SemEval 2023 Task 3, directed toward 972 press releases from ten agencies. The generated attacks come in two mediums, press release statements and social media posts, covering both long-form and short-form communication strategies. We analyzed the moral resonance of these persuasion attacks to understand their attack vectors. GPT-4's attacks mainly focus on Care, with Authority and Loyalty also playing a role. Gemma 2 emphasizes Care and Authority, while Llama 3.1 centers on Loyalty and Care. Analyzing LLM-generated persuasive attacks across models will enable proactive defense, allow to create the reputation armor for organizations, and propel the development of both effective and resilient communications in the information ecosystem.