Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning
Anonymous networks, which aim primarily to protect user identities, have gained prominence as tools for enhancing network security and anonymity. Nonetheless, these networks have become a platform for adversarial affairs and sources of suspicious attack traffic. To defend against unpredictable adver...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/7/2295 |
| _version_ | 1797211925855076352 |
|---|---|
| author | Dazhou Liu Younghee Park |
| author_facet | Dazhou Liu Younghee Park |
| author_sort | Dazhou Liu |
| collection | DOAJ |
| description | Anonymous networks, which aim primarily to protect user identities, have gained prominence as tools for enhancing network security and anonymity. Nonetheless, these networks have become a platform for adversarial affairs and sources of suspicious attack traffic. To defend against unpredictable adversaries on the Internet, detecting anonymous network traffic has emerged as a necessity. Many supervised approaches to identify anonymous traffic have harnessed machine learning strategies. However, many require access to engineered datasets and complex architectures to extract the desired information. Due to the resistance of anonymous network traffic to traffic analysis and the scarcity of publicly available datasets, those approaches may need to improve their training efficiency and achieve a higher performance when it comes to anonymous traffic detection. This study utilizes feature engineering techniques to extract pattern information and rank the feature importance of the static traces of anonymous traffic. To leverage these pattern attributes effectively, we developed a reinforcement learning framework that encompasses four key components: states, actions, rewards, and state transitions. A lightweight system is devised to classify anonymous and non-anonymous network traffic. Subsequently, two fine-tuned thresholds are proposed to substitute the traditional labels in a binary classification system. The system will identify anonymous network traffic without reliance on labeled data. The experimental results underscore that the system can identify anonymous traffic with an accuracy rate exceeding 80% (when based on pattern information). |
| first_indexed | 2024-04-24T10:34:14Z |
| format | Article |
| id | doaj.art-17187abfba114d22a865c600e2072f10 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-24T10:34:14Z |
| publishDate | 2024-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-17187abfba114d22a865c600e2072f102024-04-12T13:26:42ZengMDPI AGSensors1424-82202024-04-01247229510.3390/s24072295Anonymous Traffic Detection Based on Feature Engineering and Reinforcement LearningDazhou Liu0Younghee Park1Faculty of Computer Engineering, Charles W. Davidson College of Engineering, San Jose State University, San Jose, CA 95192, USAFaculty of Computer Engineering, Charles W. Davidson College of Engineering, San Jose State University, San Jose, CA 95192, USAAnonymous networks, which aim primarily to protect user identities, have gained prominence as tools for enhancing network security and anonymity. Nonetheless, these networks have become a platform for adversarial affairs and sources of suspicious attack traffic. To defend against unpredictable adversaries on the Internet, detecting anonymous network traffic has emerged as a necessity. Many supervised approaches to identify anonymous traffic have harnessed machine learning strategies. However, many require access to engineered datasets and complex architectures to extract the desired information. Due to the resistance of anonymous network traffic to traffic analysis and the scarcity of publicly available datasets, those approaches may need to improve their training efficiency and achieve a higher performance when it comes to anonymous traffic detection. This study utilizes feature engineering techniques to extract pattern information and rank the feature importance of the static traces of anonymous traffic. To leverage these pattern attributes effectively, we developed a reinforcement learning framework that encompasses four key components: states, actions, rewards, and state transitions. A lightweight system is devised to classify anonymous and non-anonymous network traffic. Subsequently, two fine-tuned thresholds are proposed to substitute the traditional labels in a binary classification system. The system will identify anonymous network traffic without reliance on labeled data. The experimental results underscore that the system can identify anonymous traffic with an accuracy rate exceeding 80% (when based on pattern information).https://www.mdpi.com/1424-8220/24/7/2295Toranonymous trafficfeature engineeringunsupervised learningreinforcement learning |
| spellingShingle | Dazhou Liu Younghee Park Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning Sensors Tor anonymous traffic feature engineering unsupervised learning reinforcement learning |
| title | Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning |
| title_full | Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning |
| title_fullStr | Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning |
| title_full_unstemmed | Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning |
| title_short | Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning |
| title_sort | anonymous traffic detection based on feature engineering and reinforcement learning |
| topic | Tor anonymous traffic feature engineering unsupervised learning reinforcement learning |
| url | https://www.mdpi.com/1424-8220/24/7/2295 |
| work_keys_str_mv | AT dazhouliu anonymoustrafficdetectionbasedonfeatureengineeringandreinforcementlearning AT youngheepark anonymoustrafficdetectionbasedonfeatureengineeringandreinforcementlearning |