mlsanityData to 7 Oct 2026

Toward More Generalized Malicious URL Detection Models

arXiv 2202.10027 ↗First posted 21 Feb 2022cs.LG cs.CRcited by 9

Not on the map. Why?

Abstract (arXiv)

This paper reveals a data bias issue that can severely affect the performance while conducting a machine learning model for malicious URL detection. We describe how such bias can be identified using interpretable machine learning techniques, and further argue that such biases naturally exist in the real world security data for training a classification model. We then propose a debiased training strategy that can be applied to most deep-learning based models to alleviate the negative effects from the biased features. The solution is based on the technique of self-supervised adversarial training to train deep neural networks learning invariant embedding from biased data. We conduct a wide range of experiments to demonstrate that the proposed strategy can lead to significantly better generalization capability for both CNN-based and RNN-based detection models.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 21 Feb 2022.

Builds on

13 of 23 references.

References · 13

  1. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  4. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  5. 2015The Variational Fair Autoencodercited by 223
  6. 2015Censoring Representations with an Adversarycited by 191
  7. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
  8. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  9. 2017Malware Detection by Eating a Whole EXEcited by 114
  10. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  11. 2019Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalizationcited by 43
  12. 2018URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detectioncited by 34
1 more
  1. 2016SoK: Applying Machine Learning in Security - A Surveycited by 1

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 4.

9 papers.

  1. 2024Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruningcited by 19
  2. 2024Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Promptingcited by 5
  3. 2024Enhance the Robustness of Text-Centric Multimodal Alignmentscited by 4
  4. 2025Uncertainty Profiles for LLMs: Uncertainty Source Decomposition and Adaptive Model-Metric Selectioncited by 4
  5. 2024Continuous Multi-Task Pre-training for Malicious URL Detection and Webpage Classificationcited by 3
  6. 2024Benchmarking Large Language Model Uncertainty for Prompt Optimizationcited by 2
  7. 2025From Past to Present: A Survey of Malicious URL Detection Techniques, Datasets and Code Repositoriescited by 1
  8. 2025WebGuard++:Interpretable Malicious URL Detection via Bidirectional Fusion of HTML Subgraphs and Multi-Scale Convolutional BERTcited by 1
  9. 2025Multimodal Chip Physical Design Engineer Assistantcited by 1