marco/ids.alfacom.it
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
209 Commits 1 Branch 100 Tags 9.2 MiB
cf3223b247
Commit Graph

209 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
marco370
cf3223b247 Update model comparison script to use current database detections 
Adjusted script to query existing database detections instead of a specific model version, updating column names to match the actual database schema (source_ip, risk_score, anomaly_type, log_count, last_seen, detected_at).

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 62d703c2-4658-4280-aec5-f5e7c090b266
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/RJGlbTt
 2025-11-25 08:42:06 +00:00
Marco Lanzara
c56af1cb16 🚀 Release v1.0.73 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-25 08:37:26
 2025-11-25 08:37:26 +00:00
marco370
a32700c149 Add script to compare old and new detection models 
Creates a Python script that loads old detection data, reanalyzes IPs with the new hybrid detector, and compares the results to identify differences and improvements.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: fe294b77-4492-471d-9d6e-9c924153f4d8
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/RJGlbTt
 2025-11-25 08:36:32 +00:00
Marco Lanzara
77cd8a823f 🚀 Release v1.0.72 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-25 08:24:55
 2025-11-25 08:24:55 +00:00
marco370
a47079c97c Add historical training data logging for hybrid models 
Integrate saving of training history to the database within `train_hybrid.py`, ensuring that model versioning is correctly applied for hybrid detector runs.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 9f8d0aa1-70ec-4271-b143-5f66d1d3756b
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/RJGlbTt
 2025-11-25 08:08:45 +00:00
Marco Lanzara
2a33ac82fa 🚀 Release v1.0.71 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-25 08:02:02
 2025-11-25 08:02:02 +00:00
marco370
cf094bf750 Update model version tracking for training history 
Dynamically set the model version to "2.0.0" for hybrid detectors and "1.0.0" for legacy detectors, and update the database insertion logic in `main.py` to use this dynamic version.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 25db5356-3182-4db3-be10-c524c0561b39
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/RJGlbTt
 2025-11-25 08:01:03 +00:00
Marco Lanzara
3a4d72f1e3 🚀 Release v1.0.70 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-25 07:56:24
 2025-11-25 07:56:24 +00:00
marco370
5feb691122 Fix error when hybrid detector models are not loaded 
Correctly check if the hybrid detector models are loaded by verifying the presence of `isolation_forest` instead of a non-existent `is_trained` attribute in `python_ml/main.py`.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: c8073c39-409d-45f4-a3e8-e48ce4d71e32
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/RJGlbTt
 2025-11-25 07:56:15 +00:00
Marco Lanzara
a7f55b68d7 🚀 Release v1.0.69 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-25 07:54:07
 2025-11-25 07:54:07 +00:00
marco370
08af108cfb Fix backend crash when initializing hybrid ML detector 
Corrected `main.py` to handle the `ml_analyzer` being `None` when `USE_HYBRID_DETECTOR` is true, preventing an `AttributeError` during startup.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 27f5de5e-5ed6-4ee6-9cc2-a7c448ad2334
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/XSkkaPM
 2025-11-25 07:53:47 +00:00
marco370
d086b00092 Fix system service to prevent continuous restart failures 
The systemd service for the ML backend is repeatedly failing and restarting due to an exit-code failure.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: d83d5831-e125-4886-bdea-1bb0aba2d63b
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/XSkkaPM
 2025-11-25 07:51:16 +00:00
marco370
adcf997bdd Saved progress at the end of the loop 
Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 42d78da0-9cbe-4323-88f0-1cec9233a0e9
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/XSkkaPM
 2025-11-24 18:17:52 +00:00
Marco Lanzara
b3b87333ca 🚀 Release v1.0.68 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 18:17:37
 2025-11-24 18:17:37 +00:00
marco370
f6e222d473 Correct SQL query for retrieving network traffic data 
Fixes a critical SQL syntax error in `train_hybrid.py` preventing data loading by adjusting the `INTERVAL` calculation for the `timestamp` WHERE clause.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: intermediate_checkpoint
Replit-Commit-Event-Id: fd776d7a-7ad0-46a7-9500-792cb8944915
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/XSkkaPM
 2025-11-24 18:16:21 +00:00
marco370
b88377e2d5 Adapt ML model to new database schema and automate training 
Adjusts SQL queries and feature extraction to accommodate changes in the network_logs database schema, enabling automatic weekly retraining of the ML hybrid detector.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: intermediate_checkpoint
Replit-Commit-Event-Id: f4fdd53b-f433-44d9-9f0f-63616a9eeec1
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 18:14:43 +00:00
Marco Lanzara
7e9599804a 🚀 Release v1.0.67 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 18:07:00
 2025-11-24 18:07:00 +00:00
Marco Lanzara
d384193203 🚀 Release v1.0.66 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 18:06:18
 2025-11-24 18:06:18 +00:00
marco370
04136e4303 Add script to train hybrid ML detector with real data 
Create a bash script to automate the training of the hybrid ML detector, automatically fetching database credentials from the .env file and executing the training process.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: a3c383a4-4a2c-4598-b060-f46984980561
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 18:05:04 +00:00
marco370
34bd6eb8b8 Saved progress at the end of the loop 
Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 75d43bf3-66f2-40ce-8820-e516a7014165
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 18:01:42 +00:00
Marco Lanzara
7a2b52af51 🚀 Release v1.0.65 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 17:58:33
 2025-11-24 17:58:33 +00:00
Marco Lanzara
3c68661af5 🚀 Release v1.0.64 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 17:57:38
 2025-11-24 17:57:38 +00:00
marco370
7ba039a547 Fix index out of bounds error during synthetic data testing 
Corrected an indexing error in `train_hybrid.py` by using `enumerate` to ensure accurate mapping of detections to the test dataset, resolving an `IndexError` when processing synthetic data.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: d05c3dd2-6349-426d-be9c-ec80a07ea78f
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:57:22 +00:00
marco370
0d9fda8a90 Saved progress at the end of the loop 
Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: a17bbc74-efee-4ac9-ab10-8a21deeb3932
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:56:20 +00:00
Marco Lanzara
87d84fc8ca 🚀 Release v1.0.63 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 17:53:58
 2025-11-24 17:53:58 +00:00
marco370
57afbc6eec Saved progress at the end of the loop 
Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: e99405da-a1e5-46f9-a34d-7773413667ae
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:53:04 +00:00
marco370
9fe2532217 Add timestamp to synthetic data for accurate model testing 
Add a 'timestamp' column to the synthetic dataset generation in `python_ml/dataset_loader.py` to resolve a `KeyError` during model training and testing.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: intermediate_checkpoint
Replit-Commit-Event-Id: 276a3bd4-aaee-40c9-acb7-027f23274a9f
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:52:16 +00:00
marco370
db54fc3235 Saved progress at the end of the loop 
Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 492f2652-d6c8-46dd-901b-3d25f2a4c5bb
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:50:09 +00:00
Marco Lanzara
71a186a891 🚀 Release v1.0.62 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 17:47:05
 2025-11-24 17:47:05 +00:00
marco370
8114c3e508 Saved progress at the end of the loop 
Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 222eee01-78e7-4e32-8beb-d5eb120d5da0
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:45:45 +00:00
marco370
75d3bd56a1 Simplify ML dependency to use standard Isolation Forest 
Remove problematic Extended Isolation Forest dependency and leverage existing scikit-learn fallback for Python 3.11 compatibility.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: intermediate_checkpoint
Replit-Commit-Event-Id: 89ea874d-b572-40ad-9ac7-0c77d2b7d08d
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:44:11 +00:00
marco370
132a667b2a Update ML dependency installation script for improved build isolation 
Refactor deployment script and documentation to correctly handle build isolation for ML dependencies, specifically `eif`, by leveraging environment variables and sequential installation steps.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 7a4bce6a-9957-4807-aa16-ce07daafe00f
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:35:40 +00:00
Marco Lanzara
8ad7e0bd9c 🚀 Release v1.0.61 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 17:11:49
 2025-11-24 17:11:49 +00:00
marco370
051c838840 Add ability to install ML dependencies and resolve build issues 
Update install_ml_deps.sh to use --no-build-isolation when installing eif to resolve ModuleNotFoundError during build.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 219383e3-8935-415d-8c84-77e7d6f76af8
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:06:43 +00:00
Marco Lanzara
485f3d983b 🚀 Release v1.0.60 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 17:02:58
 2025-11-24 17:02:58 +00:00
marco370
102113e950 Improve ML dependency installation script for robust deployment 
Update deployment script to correctly activate virtual environment, install Cython and numpy as build dependencies before eif, and ensure sequential installation for the ML hybrid detector.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 8b4c76c7-3a42-4713-8396-40f5db530225
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 17:02:15 +00:00
Marco Lanzara
270e211fec 🚀 Release v1.0.59 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 16:59:32
 2025-11-24 16:59:32 +00:00
Marco Lanzara
81dee61ae4 🚀 Release v1.0.58 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 16:58:25
 2025-11-24 16:58:25 +00:00
marco370
b78f03392a Update deployment process to handle machine learning dependencies 
Create a dedicated script to install machine learning dependencies in the correct order, ensuring Cython is installed before packages that require it for compilation, and update documentation accordingly.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: aa7dc534-7330-4bd4-b726-d6eeb29008af
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 16:38:41 +00:00
Marco Lanzara
f5e212626a 🚀 Release v1.0.57 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 16:36:14
 2025-11-24 16:36:14 +00:00
marco370
b4aaa5456f Add Cython to Python dependencies for model compilation 
Add Cython==3.0.5 to python_ml/requirements.txt and update replit.md to reflect this change, resolving a compilation issue with the eif library.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: f24578fc-6be7-42c0-9a9c-5ffe13dacdbe
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 16:35:15 +00:00
Marco Lanzara
152e22621b 🚀 Release v1.0.56 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 16:33:35
 2025-11-24 16:33:35 +00:00
marco370
043690f829 Update dependency version for improved compatibility 
Update `eif` dependency from version 2.0.0 to 2.0.2 in `requirements.txt` and documentation to resolve a deployment issue, as version 2.0.0 is not available.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 104a0ac7-f020-4d00-9e3e-5a37b74bbc93
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 16:32:31 +00:00
Marco Lanzara
3a945ec7d0 🚀 Release v1.0.55 
- Tipo: patch
- Database schema: database-schema/schema.sql (solo struttura)
- Data: 2025-11-24 16:28:47
 2025-11-24 16:28:47 +00:00
marco370
dac78addab Saved progress at the end of the loop 
Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: e9fa7e86-fa28-4924-9cbf-ddb3a20493fa
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 16:26:43 +00:00
marco370
16617aa0fa Improve model training by adding robust error handling and logging 
Add exception handling to the model training process to log failures and improve robustness.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: intermediate_checkpoint
Replit-Commit-Event-Id: 9c7ad6b8-3e9d-41fe-83f7-6b2a48f8ff44
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 16:25:40 +00:00
marco370
783d28f571 Add a hybrid machine learning system to reduce false positives 
Add a new hybrid ML detector system using Extended Isolation Forest and feature selection to reduce false positives. Documented with a deployment checklist and updated API performance notes.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: 80860ac4-8fe9-479b-b8fb-cb4c6804a667
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 16:06:29 +00:00
marco370
8b16800bb6 Update system to use hybrid detector and improve validation accuracy 
Update main.py endpoints to use the hybrid detector and improve validation logic in train_hybrid.py by mapping detections using source_ip. Also, add synthetic source_ip to dataset_loader.py for both CICIDS2017 and synthetic datasets.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: intermediate_checkpoint
Replit-Commit-Event-Id: 5c4982f1-3d37-47da-9253-c04888f5ff64
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/2lUhxO2
 2025-11-24 16:02:49 +00:00
marco370
4bc4bc5a31 Update backend API to support new hybrid ML detection system 
Introduce MLHybridDetector and update FastAPI app configuration to prioritize it, along with a new training script `train_hybrid.py`.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: intermediate_checkpoint
Replit-Commit-Event-Id: 462e355b-1642-45af-be7c-e04efa9dee67
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/F6DiMv4
 2025-11-24 15:57:23 +00:00
marco370
350a0994bd Add dataset loader and validation metrics modules 
Introduces `CICIDS2017Loader` for dataset handling and `ValidationMetrics` class for calculating performance metrics in Python.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: intermediate_checkpoint
Replit-Commit-Event-Id: ad530f16-3a16-44a3-8fed-6c5d56775c77
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/F6DiMv4
 2025-11-24 15:55:30 +00:00