3 papers
cs.CR2026
An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation
Kushankur Ghosh, Mehar Klair, Kian Kyars +2
Provenance graphs model causal system-level interactions from logs, enabling anomaly detectors to learn normal behavior and detect deviations as attacks. However, existing approach…
cs.LG2024
Unsupervised Parameter-free Outlier Detection using HDBSCAN* Outlier Profiles
Kushankur Ghosh, Murilo Coelho Naldi, Jörg Sander +1
In machine learning and data mining, outliers are data points that significantly differ from the dataset and often introduce irrelevant information that can induce bias in its stat…
cs.LG2021
On the combined effect of class imbalance and concept complexity in deep learning
Kushankur Ghosh, Colin Bellinger, Roberto Corizzo +2
Structural concept complexity, class overlap, and data scarcity are some of the most important factors influencing the performance of classifiers under class imbalance conditions.…