abdull66-hash/detection-under-budgets

How abdull66-hash/detection-under-budgets works

This repository is a research project evaluating flow-sampling policies for network-attack monitoring. Its principal workflow loads and cleans a dataset, splits it into training, scorer, and test sets, trains attack models, applies sampling policies, and evaluates flow- and campaign-level detection; it also compares a second regime that samples training data. Baselines, diagnostic checks, regime analyses, summary tables, and report figures are supporting research branches. Source excerpts show the experiment orchestration and key helpers; edges for other modules rely only on the SOURCE INDEX, so unsampled behavior is not inferred.

Main entry points: run_regime2.py Sampled-train regime · run_experiment.py Full-train regime · preprocess.py Clean splits · baseline.py Baseline runs

Components 20

Data preparation

Clean splits p1_monitoring_budget/src/preprocess.py

Experiments

Sampling policies p1_monitoring_budget/src/sampling.py
Campaign metrics p1_monitoring_budget/src/campaigns.py
Attack models p1_monitoring_budget/src/models.py
Baseline runs p1_monitoring_budget/src/baseline.py
Full-train regime p1_monitoring_budget/src/run_experiment.py
Sampled-train regime p1_monitoring_budget/src/run_regime2.py

Analysis and reporting

Column checks p1_monitoring_budget/src/column_check.py
Host-keyed spread p1_monitoring_budget/src/host_keyed_spread.py
Regime analysis p1_monitoring_budget/src/analyze_regimes.py
Result analysis p1_monitoring_budget/src/analyze.py
Summary tables p1_monitoring_budget/src/summary_table.py
Report figures p1_monitoring_budget/src/figures.py
Experiment results p1_monitoring_budget/results

Shared helpers

File helpers common/io.py
Metric helpers common/metrics.py
Seed control common/seed.py
Plot helpers common/plotting.py

Other components

Researcher
Flow dataset

Connections 41

Researcher → Baseline runs: runs baseline p1_monitoring_budget/src/baseline.py
Researcher → Full-train regime: runs experiment p1_monitoring_budget/src/run_experiment.py
Researcher → Sampled-train regime: runs regime p1_monitoring_budget/src/run_regime2.py
Flow dataset → Clean splits: loads and cleans p1_monitoring_budget/src/preprocess.py
Clean splits → File helpers: loads parquet p1_monitoring_budget/src/preprocess.py
Baseline runs → Clean splits: loads splits p1_monitoring_budget/src/baseline.py
Baseline runs → Attack models: builds models p1_monitoring_budget/src/baseline.py
Baseline runs → Metric helpers: scores predictions p1_monitoring_budget/src/baseline.py
Baseline runs → Seed control: sets seeds p1_monitoring_budget/src/baseline.py
Full-train regime → Clean splits: loads splits p1_monitoring_budget/src/run_experiment.py
Full-train regime → Sampling policies: builds masks p1_monitoring_budget/src/run_experiment.py
Full-train regime → Campaign metrics: measures campaigns p1_monitoring_budget/src/run_experiment.py
Full-train regime → Attack models: trains models p1_monitoring_budget/src/run_experiment.py
Full-train regime → Metric helpers: scores predictions p1_monitoring_budget/src/run_experiment.py
Full-train regime → Seed control: sets seeds p1_monitoring_budget/src/run_experiment.py
Full-train regime → File helpers: saves results p1_monitoring_budget/src/run_experiment.py
Sampled-train regime → Clean splits: loads splits p1_monitoring_budget/src/run_regime2.py
Sampled-train regime → Sampling policies: builds masks p1_monitoring_budget/src/run_regime2.py
Sampled-train regime → Campaign metrics: measures campaigns p1_monitoring_budget/src/run_regime2.py
Sampled-train regime → Attack models: trains models p1_monitoring_budget/src/run_regime2.py
Sampled-train regime → Full-train regime: reuses masks p1_monitoring_budget/src/run_regime2.py
Sampled-train regime → Metric helpers: scores predictions p1_monitoring_budget/src/run_regime2.py
Sampled-train regime → Seed control: sets seeds p1_monitoring_budget/src/run_regime2.py
Sampled-train regime → File helpers: saves results p1_monitoring_budget/src/run_regime2.py
Baseline runs → Experiment results: writes results p1_monitoring_budget/src/baseline.py
Full-train regime → Experiment results: writes results p1_monitoring_budget/src/run_experiment.py
Sampled-train regime → Experiment results: writes results p1_monitoring_budget/src/run_regime2.py
Column checks → Baseline runs: uses baseline p1_monitoring_budget/src/column_check.py
Host-keyed spread → Sampling policies: uses sampling p1_monitoring_budget/src/host_keyed_spread.py
Regime analysis → Campaign metrics: uses campaign logic p1_monitoring_budget/src/analyze_regimes.py
Regime analysis → Clean splits: uses preprocessing p1_monitoring_budget/src/analyze_regimes.py
Result analysis → Metric helpers: uses metrics p1_monitoring_budget/src/analyze.py
Summary tables → Clean splits: uses preprocessing p1_monitoring_budget/src/summary_table.py
Report figures → Clean splits: loads split data p1_monitoring_budget/src/figures.py
Report figures → Plot helpers: styles and saves p1_monitoring_budget/src/figures.py
Report figures → Experiment results: reads and writes figures p1_monitoring_budget/src/figures.py
Result analysis → File helpers: uses file helpers p1_monitoring_budget/src/analyze.py
Regime analysis → File helpers: uses file helpers p1_monitoring_budget/src/analyze_regimes.py
Summary tables → File helpers: uses file helpers p1_monitoring_budget/src/summary_table.py
Column checks → File helpers: uses file helpers p1_monitoring_budget/src/column_check.py
Host-keyed spread → File helpers: uses file helpers p1_monitoring_budget/src/host_keyed_spread.py

Drawn by GitDiagram on November 13, 2026 from the repository's file tree, README and source files. Read as Markdown ·