On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “UNSW-NB15”

Benchmarking datasets for Anomaly-based Network Intrusion Detection: KDD CUP 99 alternativescs.LG

This paper benchmarks UNSW-NB15 as a modern alternative to KDD-99 for A-NIDS.

problem Skewed response distribution and non-stationarity in KDD-99 hamper A-NIDS performance.

method Compared UNSW-NB15 to KDD-99 and NSL-KDD using various classification models and SMOTE oversampling.

result UNSW-NB15 outperforms KDD-99 and NSL-KDD in minority class performance, suggesting it as a better benchmark.

Anomaly-based Intrusion Detection KDD CUP 99 NSL-KDD UNSW-NB15 Classification Models

2018-11-13abs ↗pdf ↗

Network Intrusion Detection based on LSTM and Feature Embeddingcs.LG

Improved IDS using LSTM and embedding for network traffic data.

problem Network security threats and need for IDS to detect attacks.

method Proposes IDS models using LSTM for time-series and embedding for categorical network traffic data.

result Improves binary classification accuracy to 99.72%.

IDS LSTM embedding network security time-series

2019-11-26abs ↗pdf ↗

Adversarial Machine Learning in Network Intrusion Detection Systemscs.CR

This paper studies adversarial examples in NIDS, revealing their vulnerability.

problem Vulnerability of machine learning-based NIDS to adversarial examples.

method Used evolutionary computation and deep learning to generate adversarial examples.

result Adversarial examples cause high misclassification rates in various machine learning models.

Adversarial Machine Learning Network Intrusion Detection Evolutionary Computation Deep Learning Vulnerability

2020-04-23abs ↗pdf ↗

An Ensemble Approach toward Automated Variable Selection for Network Anomaly Detectioncs.LG

Paper automates variable selection for network anomaly detection.

problem Automating variable selection for network anomaly detection is challenging.

method Ensemble approach combining well-known selection techniques.

result Identifies a small number of core variables that approximate full-variable performance.

variable selection anomaly detection network traffic ensemble methods

2019-10-28abs ↗pdf ↗

When Individually Calibrated Models Become Collectively Miscalibratedcs.LG

Calibrated models can lead to miscalibrated aggregations in strategic interactions.

problem Miscalibration in aggregated predictions from multiple calibrated models.

method Analysis of strategic interactions between calibrated predictors, proving conditions for miscalibration and comparing VCG and Brier-score aggregation methods.

result VCG aggregation method outperforms Brier-score in strategic settings, providing robustness and comparable accuracy.

calibration strategic interaction miscalibration VCG Brier-score

2026-05-14abs ↗pdf ↗

Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generationcs.CR

This paper improves AI defenses against network attacks using ML and adversarial learning.

problem Protecting personal data from sophisticated network attacks.

method Unified multi-modal dataset, machine learning for detection, adversarial learning for synthetic data generation.

result Stable ML models for intrusion detection and high-fidelity synthetic data.

network attacks machine learning adversarial learning synthetic data intrusion detection

2026-03-18abs ↗pdf ↗

Deep Reinforcement One-Shot Learning for Artificially Intelligent Classification Systemscs.LG

DeROL tackles one-shot learning for AI systems with limited data.

problem Handling few training instances for classification tasks.

method Develops a Deep Reinforcement Learning framework to optimize resource usage.

result Demonstrates efficient resource allocation in one-shot learning.

Deep Reinforcement Learning One-Shot Learning Artificial Intelligence Resource Optimization Computer Vision

2018-08-04abs ↗pdf ↗