cyb001-baseline-classifier / validation_results.json
pradeep-xpert's picture
Initial release: XGBoost + MLP baseline on CYB001 sample
721fce4 verified
{
"version": "1.0.0",
"dataset": "xpertsystems/cyb001-sample",
"split": {
"train": 6838,
"validation": 1466,
"test": 1466,
"strategy": "stratified",
"seed": 42
},
"n_features": 101,
"label_classes": [
"BENIGN",
"MALICIOUS",
"AMBIGUOUS"
],
"class_distribution_train": {
"BENIGN": 4915,
"MALICIOUS": 1379,
"AMBIGUOUS": 544
},
"class_distribution_test": {
"BENIGN": 1054,
"MALICIOUS": 295,
"AMBIGUOUS": 117
},
"models": {
"xgboost": {
"architecture": "Gradient-boosted decision trees, multi:softprob, 3 classes",
"framework": "xgboost",
"test_metrics": {
"model": "xgboost",
"accuracy": 0.9979536152796725,
"macro_f1": 0.9961123729105247,
"weighted_f1": 0.9979537067605843,
"per_class_f1": {
"BENIGN": 0.9985761746559089,
"MALICIOUS": 0.9983079526226735,
"AMBIGUOUS": 0.9914529914529915
},
"confusion_matrix": {
"labels": [
"BENIGN",
"MALICIOUS",
"AMBIGUOUS"
],
"matrix": [
[
1052,
1,
1
],
[
0,
295,
0
],
[
1,
0,
116
]
]
},
"macro_roc_auc_ovr": 0.9999888611978185
}
},
"mlp": {
"architecture": "PyTorch MLP, 101 -> 128 -> 64 -> 3, BatchNorm1d + ReLU + Dropout, weighted cross-entropy loss",
"framework": "pytorch",
"test_metrics": {
"model": "mlp",
"accuracy": 0.9931787175989086,
"macro_f1": 0.9868796182274947,
"weighted_f1": 0.9931977860171972,
"per_class_f1": {
"BENIGN": 0.9961977186311787,
"MALICIOUS": 0.9898648648648649,
"AMBIGUOUS": 0.9745762711864406
},
"confusion_matrix": {
"labels": [
"BENIGN",
"MALICIOUS",
"AMBIGUOUS"
],
"matrix": [
[
1048,
2,
4
],
[
2,
293,
0
],
[
0,
2,
115
]
]
},
"macro_roc_auc_ovr": 0.9995571752214697
}
}
}
}