用多模型投票+微调大模型，提升诈骗检测抗攻击能力
Scam Shield: Multi-Model Voting and Fine-Tuned LLMs Against Adversarial Attacks
- 前段多模型投票筛选，后端微调LLaMA处理疑难案例
- 对抗训练使误判率下降，推理速度比纯大模型快40%
- 适合需要高鲁棒性的反诈骗系统部署
诈骗检测在网络安全中仍具挑战性，因攻击者可设计绕过自动化过滤器的消息。本文提出分层诈骗检测系统（HSDS），结合轻量级多模型投票前端与微调的LLaMA 3.1 8B Instruct后端，以提升准确率和对抗攻击的鲁棒性。四个分类器组成的集成模型通过多数投票进行初步判断，模糊案例则移交至经过对抗训练优化的微调模型处理，降低误分类。实验表明，该分层设计不仅增强对抗性诈骗检测能力，还通过将大部分案例分流至轻量前端，使推理时间缩短40%，优于传统机器学习基线和专有大模型基线。研究验证了混合投票机制与对抗微调在强化大模型应对演化诈骗策略方面的有效性，提升了自动化诈骗检测系统的韧性。
原文摘要 · Abstract (English)
Scam detection remains a critical challenge in cybersecurity as adversaries craft messages that evade automated filters. We propose a Hierarchical Scam Detection System (HSDS) that combines a lightweight multi-model voting front end with a fine-tuned LLaMA 3.1 8B Instruct back end to improve accuracy and robustness against adversarial attacks. An ensemble of four classifiers provides preliminary predictions through majority vote, and ambiguous cases are escalated to the fine-tuned model, which is optimized with adversarial training to reduce misclassification. Experiments show that this hierarchical design both improves adversarial scam detection and shortens inference time by routing most cases away from the LLM, outperforming traditional machine-learning baselines and proprietary LLM baselines. The findings highlight the effectiveness of a hybrid voting mechanism and adversarial fine-tuning in fortifying LLMs against evolving scam tactics, enhancing the resilience of automated scam detection systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。