Jacquin Antoine c6cb12981c feat(ml): replace NetworkX/Louvain with PyTorch Geometric GraphSAGE for fleet detection ...

Rewrite fleet.py to use a GNN-based approach: nodes are src_ip with ML feature
vectors, edges connect IPs sharing (JA4, ASN) pairs, GraphSAGE (2 SAGEConv
layers, in→64→32) produces 32D embeddings clustered by HDBSCAN. PyG NeighborLoader
activates for >50k nodes. Update thesis docs (§5.2, §6.4, §2, §8) to reflect
GraphSAGE architecture and PyG scalability.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-04-13 15:45:34 +02:00

..

tests

feat(ml): replace Autoencoder with RealNVP Normalizing Flow and add SessionTransformer embeddings

2026-04-13 15:11:21 +02:00

__init__.py

refactor(bot-detector): extract monolith into modular package

2026-04-09 01:02:04 +02:00

__main__.py

refactor(bot-detector): extract monolith into modular package

2026-04-09 01:02:04 +02:00

browser_matcher_dynamic.py

feat(bot-detector): add dynamic browser profiling engine with HDBSCAN clustering

2026-04-13 02:06:00 +02:00

browser_matcher.py

feat: multi-distro VM tests, ja4ebpf eBPF improvements, bot-detector scoring

2026-04-13 01:09:33 +02:00

browser_signatures.py

feat: multi-distro VM tests, ja4ebpf eBPF improvements, bot-detector scoring

2026-04-13 01:09:33 +02:00

browser.py

feat: roadmap détection bots §2-9 — HTTP/2, cohérence, drift, flotte, Jaccard, ExIFFI, méta-learner, métriques

2026-04-10 00:11:35 +02:00

config.py

feat(ml): replace Autoencoder with RealNVP Normalizing Flow and add SessionTransformer embeddings

2026-04-13 15:11:21 +02:00

cycle.py

feat(ml): replace Autoencoder with RealNVP Normalizing Flow and add SessionTransformer embeddings

2026-04-13 15:11:21 +02:00

Dockerfile

refactor(bot-detector): extract monolith into modular package

2026-04-09 01:02:04 +02:00

Dockerfile.tests

fix(docker): add g++ for isotree build, add dashboard Dockerfile.tests

2026-04-08 08:08:13 +02:00

fleet.py

feat(ml): replace NetworkX/Louvain with PyTorch Geometric GraphSAGE for fleet detection

2026-04-13 15:45:34 +02:00

infra.py

refactor(bot-detector): extract monolith into modular package

2026-04-09 01:02:04 +02:00

log.py

refactor(bot-detector): extract monolith into modular package

2026-04-09 01:02:04 +02:00

metrics.py

feat: roadmap détection bots §2-9 — HTTP/2, cohérence, drift, flotte, Jaccard, ExIFFI, méta-learner, métriques

2026-04-10 00:11:35 +02:00

models.py

feat(ml): replace Autoencoder with RealNVP Normalizing Flow and add SessionTransformer embeddings

2026-04-13 15:11:21 +02:00

pipeline.py

feat(ml): replace Autoencoder with RealNVP Normalizing Flow and add SessionTransformer embeddings

2026-04-13 15:11:21 +02:00

preprocessing.py

feat(ml): replace Autoencoder with RealNVP Normalizing Flow and add SessionTransformer embeddings

2026-04-13 15:11:21 +02:00

profile_builder.py

feat(bot-detector): add dynamic browser profiling engine with HDBSCAN clustering

2026-04-13 02:06:00 +02:00

requirements.txt

feat(ml): replace NetworkX/Louvain with PyTorch Geometric GraphSAGE for fleet detection

2026-04-13 15:45:34 +02:00

scoring.py

feat: multi-distro VM tests, ja4ebpf eBPF improvements, bot-detector scoring

2026-04-13 01:09:33 +02:00

session_transformer.py

feat(ml): replace Autoencoder with RealNVP Normalizing Flow and add SessionTransformer embeddings

2026-04-13 15:11:21 +02:00