Deep Reinforcement Learning for Phishing Detection with Transformer-Based Semantic Features

• URL: http://arxiv.org/abs/2512.06925v1
• Date: Sun, 07 Dec 2025 17:08:12 GMT
• Title: Deep Reinforcement Learning for Phishing Detection with Transformer-Based Semantic Features
• Authors: Aseer Al Faisal,
• Abstract summary: Phishing is a cybercrime in which individuals are deceived into revealing personal information.<n>This study proposes a Quantile Deep Q-Network (QR-DQN) approach that integrates RoBERTa semantic embeddings with handcrafted lexical features.<n>A diverse dataset of 105,000 URLs was curated from PhishTank, OpenPhish, Cloudflare, and other sources.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Phishing is a cybercrime in which individuals are deceived into revealing personal information, often resulting in financial loss. These attacks commonly occur through fraudulent messages, misleading advertisements, and compromised legitimate websites. This study proposes a Quantile Regression Deep Q-Network (QR-DQN) approach that integrates RoBERTa semantic embeddings with handcrafted lexical features to enhance phishing detection while accounting for uncertainties. Unlike traditional DQN methods that estimate single scalar Q-values, QR-DQN leverages quantile regression to model the distribution of returns, improving stability and generalization on unseen phishing data. A diverse dataset of 105,000 URLs was curated from PhishTank, OpenPhish, Cloudflare, and other sources, and the model was evaluated using an 80/20 train-test split. The QR-DQN framework achieved a test accuracy of 99.86%, precision of 99.75%, recall of 99.96%, and F1-score of 99.85%, demonstrating high effectiveness. Compared to standard DQN with lexical features, the hybrid QR-DQN with lexical and semantic features reduced the generalization gap from 1.66% to 0.04%, indicating significant improvement in robustness. Five-fold cross-validation confirmed model reliability, yielding a mean accuracy of 99.90% with a standard deviation of 0.04%. These results suggest that the proposed hybrid approach effectively identifies phishing threats, adapts to evolving attack strategies, and generalizes well to unseen data.

Related papers

• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• Phishing Detection System: An Ensemble Approach Using Character-Level CNN and Feature Engineering [0.0]
  This paper presents an AI model for a phishing detection system.<n>It uses an ensemble approach to combine character-level Convolutional Neural Networks (CNN) and LightGBM with engineered features.<n>On a test dataset of 19,873 URLs, the ensemble model achieves an accuracy of 99.819 percent, precision of 100 percent, recall of 99.635 percent, and ROC-AUC of 99.947 percent.
  arXiv  Detail & Related papers  (2025-12-18T16:19:12Z)
• CLUE: Non-parametric Verification from Experience via Hidden-State Clustering [64.50919789875233]
  We show that correctness of a solution is encoded as a geometrically separable signature within the trajectory of hidden activations.<n>ClUE consistently outperforms LLM-as-a-judge baselines and matches or exceeds modern confidence-based methods in reranking candidates.
  arXiv  Detail & Related papers  (2025-10-02T02:14:33Z)
• Hybrid Reputation Aggregation: A Robust Defense Mechanism for Adversarial Federated Learning in 5G and Edge Network Environments [0.0]
  Federated Learning (FL) in 5G and edge network environments face severe security threats from adversarial clients.<n>This paper introduces Hybrid Reputation Aggregation (HRA), a novel robust aggregation mechanism designed to defend against adversarial behaviors in FL without prior knowledge of the attack type.<n>HRA combines geometric anomaly detection with momentum-based reputation tracking of clients.
  arXiv  Detail & Related papers  (2025-09-22T17:18:59Z)
• Phishing URL Detection using Bi-LSTM [0.0]
  This paper proposes a deep learning-based approach to classify URLs into four categories: benign, phishing, defacement, and malware.<n> Experimental results on a dataset comprising over 650,000 URLs demonstrate the model's effectiveness, achieving 97% accuracy and significant improvements over traditional techniques.
  arXiv  Detail & Related papers  (2025-04-29T00:55:01Z)
• A Gradient-Optimized TSK Fuzzy Framework for Explainable Phishing Detection [0.0]
  Existing phishing detection methods struggle to simultaneously achieve high accuracy and explainability.<n>We propose a novel phishing URL detection system based on a first-order Takagi-Sugeno-Kang fuzzy inference model optimized through gradient-based techniques.
  arXiv  Detail & Related papers  (2025-04-25T18:31:05Z)
• Browser Extension for Fake URL Detection [0.0]
  This paper presents a Browser Extension that uses machine learning models to enhance online security. The proposed solution uses LGBM classifier for classification of Phishing websites. The Model for Spam email detection uses Multinomial NB algorithm which has been trained on a dataset with over 5500 messages.
  arXiv  Detail & Related papers  (2024-11-16T07:22:59Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering [116.4277292854053]
  Federated Learning (FL) offers collaborative model training without data sharing. FL is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. We present G$2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem.
  arXiv  Detail & Related papers  (2023-06-08T07:15:04Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data [81.00385374948125]
  We present UNcertaInTy-based hEalth risk prediction (UNITE) model. UNITE provides accurate disease risk prediction and uncertainty estimation leveraging multi-sourced health data. We evaluate UNITE on real-world disease risk prediction tasks: nonalcoholic fatty liver disease (NASH) and Alzheimer's disease (AD) UNITE achieves up to 0.841 in F1 score for AD detection, up to 0.609 in PR-AUC for NASH detection, and outperforms various state-of-the-art baselines by up to $19%$ over the best baseline.
  arXiv  Detail & Related papers  (2020-10-22T02:28:11Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• High Accuracy Phishing Detection Based on Convolutional Neural Networks [0.0]
  We present a deep learning-based approach to enable high accuracy detection of phishing sites. The proposed approach utilizes convolutional neural networks (CNN) for high accuracy classification. We evaluate the models using a dataset obtained from 6,157 genuine and 4,898 phishing websites.
  arXiv  Detail & Related papers  (2020-04-08T12:20:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.