A hybrid spam detection method based on unstructured datasets
| Autor: | Quan Shi, Marcello Trovati, Eleana Asimakopoulou, Nik Bessis, Yeqin Shao, Olga Angelopoulou |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
business.industry
Computer science 020206 networking & telecommunications Computational intelligence Feature selection 02 engineering and technology Sparse approximation Semantic property Machine learning computer.software_genre Image spam Semantic network Theoretical Computer Science Identification (information) Bag-of-words model 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Geometry and Topology Artificial intelligence Data mining business computer Software |
| Zdroj: | Soft Computing. 21:233-243 |
| ISSN: | 1433-7479 1432-7643 |
| DOI: | 10.1007/s00500-015-1959-z |
| Popis: | The identification of non-genuine or malicious messages poses a variety of challenges due to the continuous changes in the techniques utilised by cyber-criminals. In this article, we propose a hybrid detection method based on a combination of image and text spam recognition techniques. In particular, the former is based on sparse representation-based classification, which focuses on the global and local image features, and a dictionary learning technique to achieve a spam and a ham sub-dictionary. On the other hand, the textual analysis is based on semantic properties of documents to assess the level of maliciousness. More specifically, we are able to distinguish between meta-spam and real spam. Experimental results show the accuracy and potential of our approach. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink