arXiv cs.AI· Lohith Srikanth Pentapalli, Jon Salisbury, Josette Riep, Kelly Cohen·· 12 小时前AI 评分20
基于梯度优化的 TSK 模糊框架：可解释钓鱼检测
A Gradient-Optimized TSK Fuzzy Framework for Explainable Phishing Detection
AI 导读
研究者提出基于一阶 Takagi-Sugeno-Kang（TSK）模糊推理模型的钓鱼 URL 检测系统，用 Adam 优化器进行梯度参数调优。在超过 235,000 条 URL 的数据集上，5 折交叉验证平均准确率达 99.95%，AUC 为 1.00。优化后的模糊规则与隶属函数可清晰展示模型决策过程，兼顾高精度与可解释性。
正文 · 原文
Abstract:Phishing attacks represent an increasingly sophisticated and pervasive threat to individuals and organizations, causing significant financial losses, identity theft, and severe damage to institutional reputations. Existing phishing detection methods often struggle to simultaneously achieve high accuracy and explainability, either failing to detect novel attacks or operating as opaque black-box models. To address this critical gap, we propose a novel phishing URL detection system based on a first-order Takagi-Sugeno-Kang (TSK) fuzzy inference model optimized through gradient-based techniques. Our approach intelligently combines the interpretability and human-like reasoning capabilities of fuzzy logic with the precision and adaptability provided by gradient optimization methods, specifically leveraging the Adam optimizer for efficient parameter tuning. Experiments conducted using a comprehensive dataset of over 235,000 URLs demonstrate rapid convergence, exceptional predictive performance (accuracy averaging 99.95% across 5 cross-validation folds, with a perfect AUC i.e. 1.00). Furthermore, optimized fuzzy rules and membership functions improve interoperability, clearly indicating how the model makes decisions - an essential feature for cybersecurity applications. This high-performance, transparent, and interpretable phishing detection framework significantly advances current cybersecurity defenses, providing practitioners with accurate and explainable decision-making tools.
| Comments: | 14 pages, 5 figures. v2: corrected a typo in Eq.(4) |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO) |
| Cite as: | arXiv:2504.18636 [cs.CR] |
| (or arXiv:2504.18636v2 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2504.18636 arXiv-issued DOI via DataCite |
Submission history
From: Lohith Srikanth Pentapalli [view email]
[v1]
Fri, 25 Apr 2025 18:31:05 UTC (714 KB)
[v2]
Fri, 16 Oct 2026 00:23:39 UTC (584 KB)
来源：arXiv cs.AI · arxiv.org