: Insider threats remain difficult to detect because malicious actions often resemble legitimate user behaviour and may evolve gradually over time. This paper presents MLBRS, a multi-layer behavioural risk scoring framework that combines rule-based scoring, statistical deviation analysis, and Isolation Forest-based anomaly detection to generate continuous employee-level risk scores. The framework integrates behavioural indicators, personalised deviation modelling, and multivariate anomaly detection to identify both abrupt and gradual behavioural changes. Due to the limited availability of publicly accessible datasets containing database-query-level insider threat activity, a synthetic dataset was constructed to simulate organisational behaviour with temporal consistency, multiple employee roles, and diverse attack scenarios. Existing insider-threat datasets primarily capture system-level activity and do not adequately represent database interactions. Experimental evaluation demonstrates consistent detection performance, achieving an ROC-AUC of 0.978 and an F1-score of 0.88 on the synthetic dataset. Additional cross-dataset evaluation using CERT-derived behavioural traces shows reduced but stable performance under less aligned behavioural conditions. The results indicate that MLBRS provides an interpretable and scalable approach for behavioural insider threat detection across heterogeneous activity patterns.
V. L. Kartheek, Aayush Shah, Rishav Jain et al.· Proceedings of the 15th Inte...· 0 citations
Global-scale software delivery increasingly relies on distributed localization pipelines to manage multilingual content across diverse deployment environments. While Continuous Integration and Delivery (CI/CD) practices have matured, existing approaches struggle to deliver scalable and reproducible orchestration under unpredictable, high-volume workloads. VM-based infrastructures often suffer from limited elasticity and high operational overhead, especially when integrating ML components such as Neural Machine Translation (NMT), which increases complexity in resource allocation and coordination of concurrent tasks. This paper introduces a serverless CI/CD framework that reimagines localization orchestration through cloud-native, event-driven design. The framework's core innovation lies in its fine-grained function scheduling, enabling parallel execution of translation workflows with dynamic scaling and adaptive resource utilization. Stateless serverless functions eliminate idletime overhead and support deterministic reproducibility through modular encapsulation and predictable invocation. A hybrid translation model integrates NMT with Translation Memory (TM), balancing adaptive fluency with domain-specific precision while maximizing concurrency across both orchestration and translation layers. Preliminary evaluation on Microsoft Azure demonstrates the framework's operational advantages. It achieves sub-second cold-start latency and scales to $\mathbf{1, 0 0 0}$ parallel instances within 15 seconds under specific consumption plans. The framework processes a $\mathbf{1 2 0}$-word batch $\mathbf{6. 4} \times$ faster (0.25 s vs. 1.6 s) and increases per-instance throughput by 72% (43 vs. 25 strings/min), supporting a peak capacity of 43,000 strings/min. These results validate the framework's ability to meet demanding localization workloads efficiently and at scale. By shifting focus from model-level optimization to orchestration-layer efficiency, this work contributes a scalable and extensible paradigm for ML-enabled localization. It demonstrates practical applicability by delivering a resilient, cloud-native solution that enhances scalability and efficiency in real-world multilingual software localization workflows.
Neeraj Kumar Sharma, Pranav Dilip Mate, Sandeep Kanchan Pandit et al.· Annual International Compute...· 0 citations
Accurate prediction of drug sensitivity in cancer cell lines is vital for precision oncology and patient-specific therapies. However, many computational approaches fail to integrate multi-modal biological and chemical features and often struggle with high-dimensional, imbalanced pharmacogenomic data, limiting predictive accuracy and interpretability. To address these challenges, we developed a machine learning framework that integrates pharmacogenomic profiles-including mutation status, copy number alterations, and microsatellite instabil-ity-with molecular fingerprints and descriptors of 85 anticancer drugs, generated using PaDEL from SMILES strings. Data from 40 breast cancer cell lines in the Genomics of Drug Sensitivity in Cancer (GDSC) dataset were employed. A threestage feature selection strategy combining Boruta, mRMR, and XGBoost was applied to reduce drug feature dimensionality while retaining 130 cell line features. Multiple models were trained, and LightGBM, optimized with grid search, class weighting, and 3-fold cross-validation, demonstrated superior performance in handling severe class imbalance (233 sensitive vs. 3167 resistant samples). LightGBM achieved training AUROC $=0.9455$, AUPRC $\boldsymbol{=} \mathbf{0. 5 1 4 8}$, Accuracy $\boldsymbol{=} \mathbf{0. 8 4 1 5}$, F1-score = 0.4481, Recall = 0.9409, and MCC = 0.4732, underscoring its suitability for sparse biomedical datasets. Model interpretation with SHapley Additive exPlanations (SHAP) highlighted BRCA-related features, identifying cnaBRCA25 (not mutated) as a resistance marker and cnaBRCA47 (mutated) as a context-dependent biomarker, consistent with their roles in DNA repair pathways. Overall, this framework demonstrates the value of multi-modal integration and interpretable machine learning in pharmacogenomics. While results are promising, validation on larger and independent cohorts is essential to establish clinical relevance.
D. Kumari, Aiman, Sakshi Singh et al.· Annual International Compute...· 0 citations