Weighted Factors for Evaluating Anonymity

Shahbar, Khalid; Zincir-Heywood, A. Nur

doi:10.1007/978-3-319-75650-9_20

Cited by 2 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to privacy concerns and the limited availability of the dataset on anonymous traffic, researchers often gather private data or generate traffic within simulated environments [17]. In response to this challenge, the authors introduced the Anon17 dataset, logging features associated with Tor and other anonymous network traffic instances [17]. These features encompass packet header information, packet counts, and the length in bytes of each flow.…”

Section: Detecting Tor Traffic By Supervised Learningmentioning

confidence: 99%

“…The performance evaluation of some machine learning-and deep learning-based models displayed a high false positive rate in classifying Darknet traffic [13]. Moreover, due to the limited availability of public datasets, researchers have needed help accessing data about anonymous network traffic [17,18]. Consequently, training detection models can be challenging.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning

Liu,

Park

2024

Sensors

View full text Add to dashboard Cite

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).

show abstract

Section: Detecting Tor Traffic By Supervised Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning

Liu,

Park

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Rationally allocating the index weight has always been a hot spot in the study of evaluation researchers. The methods proposed until now have mainly included the subjective weight empowerment of experts [9, 10] and the objective weight‐empowerment method that extracts the index weight from index values [11, 12]. The first subject discussed in this paper is to find a more reasonable method of weight empowerment based on the comparison and analysis of the advantages and disadvantages of the subjective and objective weight‐empowerment methods.…”

Section: Introductionmentioning

confidence: 99%