Web Fraud Attacks Against LLM-Driven Multi-Agent Systems

With the proliferation of LLM-driven multi-agent systems (MAS), the security of Web links has become a critical concern. Once MAS is induced to trust a malicious link, attackers can use it as a springboard to expand the attack surface. In this paper, we propose Web Fraud Attacks, a novel type of attack manipulating unique structures of web links to deceive MAS. We design 12 representative attack variants that encompass various methods, such as homoglyph deception, sub-directory nesting, and parameter obfuscation. Through extensive experiments on these attack vectors, we demonstrate that Web fraud attacks not only exhibit significant destructive potential across different MAS architectures but also possess a distinct advantage in evasion: they circumvent the need for complex input design, lowering the threshold for attacks significantly. These results underscore the importance of addressing Web fraud attacks, providing new insights into MAS safety. Our code is available at https://github.com/JiangYingEr/Web-Fraud-Attack-in-MAS.

Key Contributions

• Proposes Web Fraud Attacks — 12 attack variants exploiting web link structures (homoglyph deception, subdirectory nesting, parameter obfuscation) to deceive LLM multi-agent systems
• Demonstrates significant destructive potential across different MAS architectures (linear, review, debate) with low attack complexity
• Evaluates three defense strategies (prompt-based safety guidelines, psychology-based detection, sandwich prevention) against the proposed attacks

🛡️ Threat Analysis

Details

Similar Papers