When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs

TL;DR

This paper investigates the malicious potential of web-enabled Large Language Models (LLMs) in cyberattacks, demonstrating their high effectiveness in data theft, impersonation, and spear-phishing, and highlighting the urgent need for security safeguards.

Contribution

It provides a comprehensive analysis of how web-enabled LLM agents can be exploited for cyberattacks, revealing their high success rates and exposing security vulnerabilities.

Findings

LLM agents achieved up to 95.9% precision in collecting PII

93.9% of impersonation posts were deemed authentic

Phishing click rates increased by 46.67% with LLM assistance

Abstract

Recent advancements in Large Language Models (LLMs) have established them as agentic systems capable of planning and interacting with various tools. These LLM agents are often paired with web-based tools, enabling access to diverse sources and real-time information. Although these advancements offer significant benefits across various applications, they also increase the risk of malicious use, particularly in cyberattacks involving personal information. In this work, we investigate the risks associated with misuse of LLM agents in cyberattacks involving personal data. Specifically, we aim to understand: 1) how potent LLM agents can be when directed to conduct cyberattacks, 2) how cyberattacks are enhanced by web-based tools, and 3) how affordable and easy it becomes to launch cyberattacks using LLM agents. We examine three attack scenarios: the collection of Personally Identifiable Information (PII), the generation of impersonation posts, and the creation of spear-phishing emails. Our experiments reveal the effectiveness of LLM agents in these attacks: LLM agents achieved a precision of up to 95.9% in collecting PII, generated impersonation posts where 93.9% of them were deemed authentic, and boosted click rate of phishing links in spear phishing emails by 46.67%. Additionally, our findings underscore the limitations of existing safeguards in contemporary commercial LLMs, emphasizing the urgent need for robust security measures to prevent the misuse of LLM agents.