Extracting Cyber Threat Intelligence from Hacker Forums: Support Vector Machines versus Convolutional Neural Networks
| Title | Extracting Cyber Threat Intelligence from Hacker Forums: Support Vector Machines versus Convolutional Neural Networks |
| Publication Type | Conference Paper |
| Year of Publication | 2017 |
| Authors | Deliu, I., Leichter, C., Franke, K. |
| Conference Name | 2017 IEEE International Conference on Big Data (Big Data) |
| ISBN Number | 978-1-5386-2715-0 |
| Keywords | Computer crime, Computer hacking, Convolutional Neural Network algorithms, convolutional neural networks, cyber security, cyber security threats, cyber threat intelligence, Cyber Threat Intelligence (CTI), data mining, error-prone process, feedforward neural nets, hacker forum, hacker forums, learning (artificial intelligence), Learning systems, machine learning, Metrics, Open-Source Intelligence, pattern classification, privacy, pubcrawl, relevant threat information, relevant threat intelligence, Support vector machines, text classification, threat vectors, vital information |
| Abstract | Hacker forums and other social platforms may contain vital information about cyber security threats. But using manual analysis to extract relevant threat information from these sources is a time consuming and error-prone process that requires a significant allocation of resources. In this paper, we explore the potential of Machine Learning methods to rapidly sift through hacker forums for relevant threat intelligence. Utilizing text data from a real hacker forum, we compared the text classification performance of Convolutional Neural Network methods against more traditional Machine Learning approaches. We found that traditional machine learning methods, such as Support Vector Machines, can yield high levels of performance that are on par with Convolutional Neural Network algorithms. |
| URL | https://ieeexplore.ieee.org/document/8258359/ |
| DOI | 10.1109/BigData.2017.8258359 |
| Citation Key | deliu_extracting_2017 |
- learning (artificial intelligence)
- vital information
- threat vectors
- text classification
- Support vector machines
- relevant threat intelligence
- relevant threat information
- pubcrawl
- privacy
- pattern classification
- Open-Source Intelligence
- Metrics
- machine learning
- Learning systems
- Computer crime
- hacker forums
- hacker forum
- feedforward neural nets
- error-prone process
- Data mining
- Cyber Threat Intelligence (CTI)
- cyber threat intelligence
- cyber security threats
- cyber security
- convolutional neural networks
- Convolutional Neural Network algorithms
- Computer hacking