arXiv subjects

Yasameen Sajid Razooqi

Publications and source records attributed to Yasameen Sajid Razooqi.

3 recordsLinked to original sources

arXiv2026

Matched-View Cross-Domain Evaluation of WireGuard VPN Traffic Classification Using Early-Flow Fingerprints

Classifying VPN-encrypted traffic by application category typically relies on datasets that collect non-VPN and VPN traffic in separate sessions, conflating encapsulation effects with session-level differences in user behavior, timing, and application mix. We use a recently published WireGuard tunnel dataset in which pre- and post-tunnel traffic is captured simultaneously, with a packet-level match ratio above 99.9%. This matched-capture design eliminates session-level confounds and enables a cross-domain benchmark: models are trained on non-VPN flows and tested on the VPN view of the same underlying flows. We compare whole-flow statistical aggregates (FlowFeatures) and Sequence of Packet Length and Time (SPLT) early-flow fingerprints across Random Forest, XGBoost, and a multi-scale CNN1D. Cross-domain transfer depends jointly on representation and model: tree ensembles achieve balanced accuracy of 0.84-0.93 with FlowFeatures but only 0.60-0.75 with flattened SPLT, whereas CNN1D processes the same SPLT fingerprint as a sequence and achieves the strongest transfer overall (balanced accuracy 0.98, macro F1 0.89) without any VPN data during training.

cs.NI↗

arXiv2025

Binary VPN Traffic Detection Using Wavelet Features and Machine Learning

Encrypted traffic classification faces growing challenges as encryption renders traditional deep packet inspection ineffective. This study addresses binary VPN detection, distinguishing VPN-encrypted from non-VPN traffic using wavelet transform-based features across multiple machine learning models. Unlike previous studies focused on application-level classification within encrypted traffic, we specifically evaluate the fundamental task of VPN identification regardless of application type. We analyze the impact of wavelet decomposition levels and dataset filtering on classification performance across significantly imbalanced data, where filtering reduces some traffic categories by up to 95%. Our results demonstrate that Random Forest (RF) achieves superior performance with an F1-score of 99%, maintaining robust accuracy even after significant dataset filtering. Neural Networks (NN) show comparable effectiveness with an F1-score of 98% when trained on wavelet level 12, while Support Vector Machines (SVM) exhibit notable sensitivity to dataset reduction, with F1-scores dropping from 90% to 85% after filtering. Comparing wavelet decomposition at levels 5 and 12, we observe improved classification performance at level 12, particularly for variable traffic types, though the marginal gains may not justify the additional computational overhead. These findings establish RF as the most reliable model for VPN traffic classification while highlighting key performance tradeoffs in feature extraction and preprocessing.

cs.NI↗

arXiv2024

Optimize Energy Consumption of Wireless Sensor Networks by using modified Ant Colony Optimization ACO

Routing represents a pivotal concern in the context of Wireless Sensor Networks (WSN) owing to its divergence from traditional network routing paradigms. The inherent dynamism of the WSN environment, coupled with the scarcity of available resources, engenders considerable challenges for industry and academia alike in devising efficient routing strategies. Addressing these challenges, a viable recourse lies in applying heuristic search methodologies to ascertain the most optimal path in WSNs. Ant Colony Optimization (ACO) is a well-established heuristic algorithm that has demonstrated notable advancements in routing contexts. This paper introduces a modify routing protocols based on Ant colony optimization. In these protocols, we incorporate the inverse of the distance between nodes and their neighbours in the probability equations of ACO along with considering pheromone levels and residual energy. These formulation modifications facilitate the selection of the most suitable candidate for the subsequent hop, effectively minimizing the average energy consumption across all nodes in each iteration. Furthermore, in this protocol, we iteratively fine-tune ACO's parameter values based on the outcomes of several experimental trials. The experimental analysis is conducted through a diverse set of network topologies, and the results are subjected to comparison against well-established ACO algorithm and routing protocols. The efficacy of the proposed protocol is assessed based on various performance metrics, encompassing throughput, energy consumption, network lifetime, energy consumption, the extent of data transferred over the network, and the length of paths traversed by packets. These metrics collectively provide a comprehensive evaluation of the performance attainments of the routing protocols.

cs.NI↗