# FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks

arXiv: https://arxiv.org/abs/2601.22485 · HTML: https://mlsanity.com/paper/2601.22485/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 48 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization](https://mlsanity.com/paper/2311.09096/) (2023)
- [FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making](https://mlsanity.com/paper/2407.06567/) (2024)
- [Text Classification via Large Language Models](https://mlsanity.com/paper/2305.08377/) (2023)
- [Combating Misinformation in the Age of LLMs: Opportunities and Challenges](https://mlsanity.com/paper/2311.05656/) (2023)
- [Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements](https://mlsanity.com/paper/2502.12904/) (2025)
- [Integration of Large Language Models and Federated Learning](https://mlsanity.com/paper/2307.08925/) (2023)
- [Post-Training Attribute Unlearning in Recommender Systems](https://mlsanity.com/paper/2403.06737/) (2024)
- [ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis](https://mlsanity.com/paper/2403.06932/) (2024)
- [Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools](https://mlsanity.com/paper/2509.21011/) (2025)
- [EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint](https://mlsanity.com/paper/2509.03058/) (2025)
- [Efficient Query-Based Attack against ML-Based Android Malware Detection under Zero Knowledge Setting](https://mlsanity.com/paper/2309.01866/) (2023)
- [Combating Phone Scams with LLM-based Detection: Where Do We Stand?](https://mlsanity.com/paper/2409.11643/) (2024)
- [HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs](https://mlsanity.com/paper/2503.02003/) (2025)
- [ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement](https://mlsanity.com/paper/2402.06221/) (2024)
- [On the Security Risks of ML-based Malware Detection Systems: A Survey](https://mlsanity.com/paper/2505.10903/) (2025)

## Built on by (most cited first, 4 of 4)

- [ACIArena: Toward Unified Evaluation for Agent Cascading Injection](https://mlsanity.com/paper/2604.07775/) (2026)
- [Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors](https://mlsanity.com/paper/2604.12359/) (2026)
- [Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation](https://mlsanity.com/paper/2604.10071/) (2026)
- [The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails](https://mlsanity.com/paper/2608.01373/) (2026)

## Abstract (arXiv)

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.