SpearBot: Leveraging Large Language Models in a Generative-Critique Framework for Spear-Phishing Email Generation

TL;DR

This paper introduces SpearBot, a framework using large language models to generate highly convincing spear-phishing emails that can evade detection, highlighting the risks posed by advanced AI in malicious content creation.

Contribution

SpearBot is a novel adversarial framework that leverages LLMs with critique mechanisms to produce more deceptive spear-phishing emails, demonstrating increased evasion of automated and human detection.

Findings

Generated emails often evade machine detection.

Human evaluations confirm high readability and deception.

SpearBot enhances phishing effectiveness against defenses.

Abstract

Large Language Models (LLMs) are increasingly capable, aiding in tasks such as content generation, yet they also pose risks, particularly in generating harmful spear-phishing emails. These emails, crafted to entice clicks on malicious URLs, threaten personal information security. This paper proposes an adversarial framework, SpearBot, which utilizes LLMs to generate spear-phishing emails with various phishing strategies. Through specifically crafted jailbreak prompts, SpearBot circumvents security policies and introduces other LLM instances as critics. When a phishing email is identified by the critic, SpearBot refines the generated email based on the critique feedback until it can no longer be recognized as phishing, thereby enhancing its deceptive quality. To evaluate the effectiveness of SpearBot, we implement various machine-based defenders and assess how well the phishing emails generated could deceive them. Results show these emails often evade detection to a large extent, underscoring their deceptive quality. Additionally, human evaluations of the emails' readability and deception are conducted through questionnaires, confirming their convincing nature and the significant potential harm of the generated phishing emails.