marco/ids.alfacom.it
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix permission errors to allow saving machine learning models

Browse Source 
Correct ownership of the models directory to allow the ML training process to save generated models.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 51de2a29-c1c5-4d67-b236-7a1824b5b0d1
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/jFtLBWL
This commit is contained in:
marco370 2025-11-25 17:40:13 +00:00
parent 42541724cf
commit c4546f843f
1 changed files with 66 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
attached_assets/Pasted--tail-f-var-log-ids-ml-backend-log-HYBRID-Mode-Hybrid-IF-Ensemble-ML-Hybrid-detector-mo-1764092371597_1764092371597.txt Normal file
View File

@ -0,0 +1,66 @@
tail -f /var/log/ids/ml_backend.log
[HYBRID] Mode: Hybrid (IF + Ensemble)
[ML] ✓ Hybrid detector models loaded and ready
 Starting IDS API on http://0.0.0.0:8000
 Docs available at http://0.0.0.0:8000/docs
INFO: 127.0.0.1:45342 - "GET /stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:49754 - "GET /stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:50634 - "GET /stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:39232 - "GET /stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:35736 - "GET /stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:37462 - "GET /stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59676 - "GET /stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:34256 - "GET /health HTTP/1.1" 200 OK
INFO: 127.0.0.1:34256 - "GET /services/status HTTP/1.1" 200 OK
INFO: 127.0.0.1:34256 - "GET /stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:34264 - "POST /train HTTP/1.1" 200 OK
[TRAIN] Inizio training...
INFO: 127.0.0.1:34264 - "GET /stats HTTP/1.1" 200 OK
[TRAIN] Trovati 100000 log per training
[TRAIN] Addestramento modello...
[TRAIN] Using Hybrid ML Detector
[HYBRID] Training hybrid model on 100000 logs...
INFO: 127.0.0.1:41612 - "GET /stats HTTP/1.1" 200 OK
Traceback (most recent call last):
File "/opt/ids/python_ml/main.py", line 201, in do_training
result = ml_detector.train_unsupervised(df)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/ids/python_ml/ml_hybrid_detector.py", line 467, in train_unsupervised
self.save_models()
File "/opt/ids/python_ml/ml_hybrid_detector.py", line 658, in save_models
joblib.dump(self.ensemble_classifier, self.model_dir / "ensemble_classifier_latest.pkl")
File "/opt/ids/python_ml/venv/lib64/python3.11/site-packages/joblib/numpy_pickle.py", line 552, in dump
with open(filename, 'wb') as f:
^^^^^^^^^^^^^^^^^^^^
PermissionError: [Errno 13] Permission denied: 'models/ensemble_classifier_latest.pkl'
[HYBRID] Extracted features for 1430 unique IPs
[HYBRID] Pre-training Isolation Forest for feature selection...
[HYBRID] Generated 43 pseudo-anomalies from pre-training IF
[HYBRID] Feature selection: 25 → 18 features
[HYBRID] Selected features: total_packets, total_bytes, conn_count, avg_packet_size, bytes_per_second... (+13 more)
[HYBRID] Normalizing features...
[HYBRID] Training Extended Isolation Forest (contamination=0.03)...
[HYBRID] Generating pseudo-labels from Isolation Forest...
[HYBRID] Pseudo-labels: 43 anomalies, 1387 normal
[HYBRID] Training ensemble classifier (DT + RF + XGBoost)...
[HYBRID] Class distribution OK: [0 1] (counts: [1387 43])
[HYBRID] Ensemble .fit() completed successfully
[HYBRID] ✅ Ensemble verified: produces 2 class probabilities
[HYBRID] Ensemble training completed and verified!
[TRAIN ERROR] ❌ Errore durante training: [Errno 13] Permission denied: 'models/ensemble_classifier_latest.pkl'
INFO: 127.0.0.1:45694 - "GET /stats HTTP/1.1" 200 OK
^C
(venv) [root@ids python_ml]# ls models/
ensemble_classifier_20251124_185541.pkl feature_names.json feature_selector_latest.pkl isolation_forest_20251125_183830.pkl scaler_20251124_192122.pkl
ensemble_classifier_20251124_185920.pkl feature_selector_20251124_185541.pkl isolation_forest.joblib isolation_forest_latest.pkl scaler_20251125_090356.pkl
ensemble_classifier_20251124_192109.pkl feature_selector_20251124_185920.pkl isolation_forest_20251124_185541.pkl metadata_20251124_185541.json scaler_20251125_092703.pkl
ensemble_classifier_20251124_192122.pkl feature_selector_20251124_192109.pkl isolation_forest_20251124_185920.pkl metadata_20251124_185920.json scaler_20251125_120016.pkl
ensemble_classifier_20251125_090356.pkl feature_selector_20251124_192122.pkl isolation_forest_20251124_192109.pkl metadata_20251124_192109.json scaler_20251125_181945.pkl
ensemble_classifier_20251125_092703.pkl feature_selector_20251125_090356.pkl isolation_forest_20251124_192122.pkl metadata_20251124_192122.json scaler_20251125_182742.pkl
ensemble_classifier_20251125_120016.pkl feature_selector_20251125_092703.pkl isolation_forest_20251125_090356.pkl metadata_20251125_092703.json scaler_20251125_183049.pkl
ensemble_classifier_20251125_181945.pkl feature_selector_20251125_120016.pkl isolation_forest_20251125_092703.pkl metadata_latest.json scaler_20251125_183830.pkl
ensemble_classifier_20251125_182742.pkl feature_selector_20251125_181945.pkl isolation_forest_20251125_120016.pkl scaler.joblib scaler_latest.pkl
ensemble_classifier_20251125_183049.pkl feature_selector_20251125_182742.pkl isolation_forest_20251125_181945.pkl scaler_20251124_185541.pkl
ensemble_classifier_20251125_183830.pkl feature_selector_20251125_183049.pkl isolation_forest_20251125_182742.pkl scaler_20251124_185920.pkl
ensemble_classifier_latest.pkl feature_selector_20251125_183830.pkl isolation_forest_20251125_183049.pkl scaler_20251124_192109.pkl
(venv) [root@ids python_ml]#