Searcharxiv⌕ Search

arXiv subjects

Syed Ibrahim

Publications and source records attributed to Syed Ibrahim.

2 recordsLinked to original sources

ST-GAT: A Leakage-Free Spatio-Temporal Graph Attention Framework for Robust Network Intrusion Detection

Intrusion detection systems are a central defence in modern networks. Deep learning models report strong anomaly-detection results, but evaluations on standard benchmarks such as CSE-CIC-IDS-2018 are often inflated by two methodological problems: temporal leakage from overlapping sliding windows, and contamination from preprocessing fitted before the train/test split. Per-flow classifiers also ignore the spatio-temporal dependencies across sequences of network flows. We propose a Spatio-Temporal Graph Attention Network (ST-GAT) that represents traffic as a sequence of graph snapshots. It builds k-Nearest Neighbour (k-NN) edges within each window, applies multi-head Graph Attention Network (GAT) layers for spatial aggregation, and uses a Bidirectional Long Short-Term Memory (BiLSTM) network with temporal attention for sequence modelling. To prevent leakage, we use non-overlapping temporal windows (stride equal to window length) and fit all preprocessing on the training split only. We compare three class-imbalance strategies: inverse class-frequency weighting, dynamic balanced sampling, and few-shot metric prototyping. Across three random seeds, ST-GAT with inverse class weighting reached a Macro-F1 of 96.65% (+/- 0.87) and an accuracy of 99.14%. This is 14.3 percentage points higher in Macro-F1 than a per-flow Random Forest baseline (82.34%). Balanced sampling reduced Macro-F1 by 2.3 points (to 94.37%) relative to loss weighting. This suggests that aggressive resampling of small, noisy minority classes can hurt detection in heavily imbalanced traffic.

cs.CR↗

Investigation of two coronal mass ejections from circular ribbon source region: Origin, Sun-Earth propagation and Geo-effectiveness

In this article, we compare the properties of two coronal mass ejections (CMEs) that show similar source region characteristics but different evolutionary behavior in the later phases. We discuss the two events in terms of their near-Sun characteristics, interplanetary evolution, and geo-effectiveness. We carefully analyzed the initiation and propagation parameters of these events to establish the precise CME-ICME connection and their near-Earth consequences. The First event was associated with poor geo-magentic storm disturbance index (Dst $\approx$-20 nT) while the second event is associated with intense geomagnetic storm of DST $\approx$-119 nT. The configuration of the sunspots in the active regions and their evolution are observed by Helioseismic and Magnetic Imager (HMI). For source region imaging, we rely on data obtained from Atmospheric Imaging Assembly (AIA) on board Solar Dynamics Observatory (SDO) and H$α$ filtergrams from Solar Tower Telescope at Aryabhatta Research Institute of Observational Sciences (ARIES). For both the CMEs, flux rope eruptions from the source region triggered flares of similar intensities ($\approx$M1). At the solar source region of the eruptions, we observed circular ribbon flare (CRF) for both the cases, suggesting fan-spine magnetic configuration in the active region corona.

astro-ph.SR↗