A Hybrid Deep Learning and Anomaly Detection Framework for Real-Time Malicious URL Classification

• URL: http://arxiv.org/abs/2512.03462v1
• Date: Sun, 30 Nov 2025 21:25:14 GMT
• Title: A Hybrid Deep Learning and Anomaly Detection Framework for Real-Time Malicious URL Classification
• Abstract summary: Malicious URLs are a primary vector for phishing, malware, and cyberthreats.<n>This study proposes a deep learning framework combining textttHashingHashizer n-gram analysis, SMOTE balancing, Isolation Forest anomaly filtering, and a lightweight neural network classifier for real-time URL classification.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Malicious URLs remain a primary vector for phishing, malware, and cyberthreats. This study proposes a hybrid deep learning framework combining \texttt{HashingVectorizer} n-gram analysis, SMOTE balancing, Isolation Forest anomaly filtering, and a lightweight neural network classifier for real-time URL classification. The multi-stage pipeline processes URLs from open-source repositories with statistical features (length, dot count, entropy), achieving $O(NL + EBdh)$ training complexity and a 20\,ms prediction latency. Empirical evaluation yields 96.4\% accuracy, 95.4\% F1-score, and 97.3\% ROC-AUC, outperforming CNN (94.8\%) and SVM baselines with a $50\!\times$--$100\!\times$ speedup (Table~\ref{tab:comp-complexity}). A multilingual Tkinter GUI (Arabic/English/French) enables real-time threat assessment with clipboard integration. The framework demonstrates superior scalability and resilience against obfuscated URL patterns.

Related papers

• A Hybrid, Multi-Layered Pipeline for Phishing and Threat Classification: Independently Validated URL and NLP Engines with a Calibrated Multi-Channel Fusion Stage [0.0]
  We present a hybrid pipeline that scores each modality with its own engine and fuses the results.<n>Three engines are built, deployed, and independently benchmarked.<n>For deployable detection, the limiting factor is how well a model generalizes.
  arXiv  Detail & Related papers  (2026-06-19T18:59:36Z)
• Benchmarking Speech-to-Speech Translation Models [55.00303727199927]
  Speech-to-speech translation (S2ST) has advanced rapidly, but offline evaluation lacks a unified protocol.<n>We introduce a benchmarking framework integrating 46 metrics across eight dimensions.<n>We deploy it on 1,248 model-language configurations from FLEURS and CVSS.
  arXiv  Detail & Related papers  (2026-06-02T07:01:33Z)
• A Lightweight Hybrid MLP-Based Framework for Real-Time Phishing URL Detection Using Structural URL Features [0.0]
  This paper proposes a lightweight hybrid framework for real-time phishing URL detection.<n>It combines blacklist-based screening with a Multi-Layer Perceptron (MLP) operating solely on structural URL features.<n>The framework extracts 16 URL-derived features capturing structural, domain-based, and security-related characteristics.
  arXiv  Detail & Related papers  (2026-05-30T20:47:58Z)
• Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs [75.62489398666644]
  We show that an emphautoresearch-style pipeline citepkarpathy2026autoresearch powered by Claude Code discovers novel white-box adversarial attack.<n>textbfsignificantly outperform all existing (30+ methods) in jailbreaking and prompt injection evaluations.
  arXiv  Detail & Related papers  (2026-03-25T16:50:56Z)
• SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks [53.97948802255959]
  We propose a framework that trains a multi-turn attacker without relying on any existing strategies or external data.<n>Prefilling self-tuning enables usable rollouts by fine-tuning on non-refusal, well-structured, multi-turn adversarial prompts.<n>We anchor harmful intent in multi-turn jailbreaks via an intent-drift-aware reward that combines intent alignment, compliance risk, and level of detail.
  arXiv  Detail & Related papers  (2026-02-06T16:44:57Z)
• 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)
• A Graph-Attentive LSTM Model for Malicious URL Detection [0.0]
  Blacklist detection methods fail to identify new or obfuscated URLs because they depend on pre-existing patterns.<n>This work presents a hybrid deep learning model named GNN-GAT-LSTM that combines Graph Neural Networks (GNNs) with Graph Attention Networks (GATs) and Long Short-Term Memory (LSTM) networks.<n>The model transforms URLs into graphs through a process where characters become nodes that connect through edges.
  arXiv  Detail & Related papers  (2025-10-12T17:10:29Z)
• Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity [63.56009745101597]
  Spiking Neural Networks (SNNs) often suffer from high time complexity $O(T)$ due to the sequential processing of $T$ spikes.<n>We propose a novel Fixed-point Parallel Training (FPT) method to accelerate SNN training without modifying the network architecture.
  arXiv  Detail & Related papers  (2025-06-10T13:27:27Z)
• vCache: Verified Semantic Prompt Caching [95.16654660556975]
  This paper proposes vCache, the first verified semantic cache with user-defined error rate guarantees.<n>It employs an online learning algorithm to estimate an optimal threshold for each cached prompt, enabling reliable cache responses without additional training.<n>Our experiments show that vCache consistently meets the specified error bounds while outperforming state-of-the-art static-threshold and fine-tuned embedding baselines.
  arXiv  Detail & Related papers  (2025-02-06T04:16:20Z)
• Hybrid Machine Learning Approach For Real-Time Malicious Url Detection Using Som-Rmo And Rbfn With Tabu Search Optimization [0.0]
  The proliferation of malicious URLs has become a significant threat to internet security. Traditional detection methods struggle to keep pace with the evolving nature of these threats. We propose a hybrid machine learning approach combining efficient feature extraction with accurate classification.
  arXiv  Detail & Related papers  (2024-07-05T07:24:49Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• A Quadratic Synchronization Rule for Distributed Deep Learning [66.68264684667562]
  This work proposes a theory-grounded method for determining $H$, named the Quadratic Synchronization Rule (QSR) Experiments on ResNet and ViT show that local gradient methods with QSR consistently improve the test accuracy over other synchronization strategies.
  arXiv  Detail & Related papers  (2023-10-22T21:38:57Z)
• A New Deep Boosted CNN and Ensemble Learning based IoT Malware Detection [0.0]
  Security issues are threatened in various types of networks, especially in the Internet of Things (IoT) environment. We have developed a new malware detection framework, Deep Squeezed-Boosted and Ensemble Learning (DSBEL), comprised of novel Squeezed-Boosted Boundary-Region Split-Transform-Merge (SB-BR-STM) CNN and ensemble learning.
  arXiv  Detail & Related papers  (2022-12-15T18:14:51Z)
• IRLI: Iterative Re-partitioning for Learning to Index [104.72641345738425]
  Methods have to trade between obtaining high accuracy while maintaining load balance and scalability in distributed settings. We propose a novel approach called IRLI, which iteratively partitions the items by learning the relevant buckets directly from the query-item relevance data. We mathematically show that IRLI retrieves the correct item with high probability under very natural assumptions and provides superior load balancing.
  arXiv  Detail & Related papers  (2021-03-17T23:13:25Z)
• Masked Contrastive Representation Learning for Reinforcement Learning [202.8261654227565]
  CURL, which uses contrastive learning to extract high-level features from raw pixels of individual video frames, is an efficient algorithm. We propose a new algorithm, masked contrastive representation learning for RL, that takes the correlation among consecutive inputs into consideration. Our method achieves consistent improvements over CURL on $14$ out of $16$ environments from DMControl suite and $21$ out of $26$ environments from Atari 2600 Games.
  arXiv  Detail & Related papers  (2020-10-15T02:00:10Z)
• Phishing URL Detection Through Top-level Domain Analysis: A Descriptive Approach [3.494620587853103]
  This study aims to develop a machine-learning model to detect fraudulent URLs which can be used within the Splunk platform. Inspired from similar approaches in the literature, we trained the SVM and Random Forests algorithms using malicious and benign datasets. We evaluated the algorithms' performance with precision and recall, reaching up to 85% precision and 87% recall in the case of Random Forests.
  arXiv  Detail & Related papers  (2020-05-13T21:41:29Z)

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.