FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915762142183424 |
|---|---|
| author | Xu, Naen Zhang, Jinghuai He, Ping Zhou, Chunyi Wang, Jun Fu, Zhihui Du, Tianyu Wang, Zhaoxiang Ji, Shouling |
| author_facet | Xu, Naen Zhang, Jinghuai He, Ping Zhou, Chunyi Wang, Jun Fu, Zhihui Du, Tianyu Wang, Zhaoxiang Ji, Shouling |
| contents | Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible to manipulation by fraudulent information, which can lead to harmful outcomes. Although advanced defense methods have been developed to address this issue, they often exhibit limitations in effectiveness, interpretability, and generalizability, particularly when applied to LLM-based applications. To address these challenges, we introduce FraudShield, a novel framework designed to protect LLMs from fraudulent content by leveraging a comprehensive analysis of fraud tactics. Specifically, FraudShield constructs and refines a fraud tactic-keyword knowledge graph to capture high-confidence associations between suspicious text and fraud techniques. The structured knowledge graph augments the original input by highlighting keywords and providing supporting evidence, guiding the LLM toward more secure responses. Extensive experiments show that FraudShield consistently outperforms state-of-the-art defenses across four mainstream LLMs and five representative fraud types, while also offering interpretable clues for the model's generations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22485 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks Xu, Naen Zhang, Jinghuai He, Ping Zhou, Chunyi Wang, Jun Fu, Zhihui Du, Tianyu Wang, Zhaoxiang Ji, Shouling Cryptography and Security Artificial Intelligence Computation and Language Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible to manipulation by fraudulent information, which can lead to harmful outcomes. Although advanced defense methods have been developed to address this issue, they often exhibit limitations in effectiveness, interpretability, and generalizability, particularly when applied to LLM-based applications. To address these challenges, we introduce FraudShield, a novel framework designed to protect LLMs from fraudulent content by leveraging a comprehensive analysis of fraud tactics. Specifically, FraudShield constructs and refines a fraud tactic-keyword knowledge graph to capture high-confidence associations between suspicious text and fraud techniques. The structured knowledge graph augments the original input by highlighting keywords and providing supporting evidence, guiding the LLM toward more secure responses. Extensive experiments show that FraudShield consistently outperforms state-of-the-art defenses across four mainstream LLMs and five representative fraud types, while also offering interpretable clues for the model's generations. |
| title | FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks |
| topic | Cryptography and Security Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2601.22485 |