cyb009-baseline-classifier / ablation_results.json
pradeep-xpert's picture
Initial release: vulnerability_class baseline + comprehensive 8-oracle-path leakage diagnostic on CYB009 sample
e520bf1 verified
{
"purpose": "Quantify how much each feature group contributes to the honest XGBoost score. Identical architecture, same stratified split, with one feature group dropped at a time.",
"full_model_metrics": {
"model": "xgboost",
"accuracy": 0.23737373737373738,
"macro_f1": 0.22437482872901052,
"weighted_f1": 0.23213786276177156,
"per_class_f1": {
"auth_access_control": 0.14583333333333334,
"cryptographic_failure": 0.21686746987951808,
"information_disclosure": 0.2909090909090909,
"injection_family": 0.23728813559322035,
"logic_flaw": 0.08955223880597014,
"memory_corruption": 0.3333333333333333,
"misconfiguration": 0.2589928057553957,
"supply_chain_weakness": 0.2222222222222222
},
"confusion_matrix": {
"labels": [
"auth_access_control",
"cryptographic_failure",
"information_disclosure",
"injection_family",
"logic_flaw",
"memory_corruption",
"misconfiguration",
"supply_chain_weakness"
],
"matrix": [
[
7,
7,
0,
11,
6,
10,
7,
5
],
[
4,
9,
3,
5,
3,
5,
16,
0
],
[
3,
0,
8,
1,
4,
0,
7,
0
],
[
3,
6,
1,
14,
8,
20,
6,
7
],
[
4,
4,
5,
3,
3,
2,
13,
0
],
[
11,
3,
0,
13,
3,
27,
5,
8
],
[
6,
9,
15,
2,
5,
7,
18,
3
],
[
5,
0,
0,
4,
1,
21,
2,
8
]
]
},
"macro_roc_auc_ovr": 0.6837125710196055
},
"ablations": {
"no_cvss": {
"n_features": 55,
"dropped_count": 2,
"metrics": {
"model": "xgboost_no_cvss",
"accuracy": 0.21212121212121213,
"macro_f1": 0.19261691542621184,
"weighted_f1": 0.20621456669040633,
"per_class_f1": {
"auth_access_control": 0.14285714285714285,
"cryptographic_failure": 0.09523809523809523,
"information_disclosure": 0.14705882352941177,
"injection_family": 0.23728813559322035,
"logic_flaw": 0.16216216216216217,
"memory_corruption": 0.33121019108280253,
"misconfiguration": 0.2028985507246377,
"supply_chain_weakness": 0.2222222222222222
},
"confusion_matrix": {
"labels": [
"auth_access_control",
"cryptographic_failure",
"information_disclosure",
"injection_family",
"logic_flaw",
"memory_corruption",
"misconfiguration",
"supply_chain_weakness"
],
"matrix": [
[
6,
3,
0,
13,
7,
12,
7,
5
],
[
3,
3,
8,
3,
7,
5,
12,
4
],
[
2,
1,
5,
0,
5,
2,
8,
0
],
[
1,
3,
3,
14,
2,
20,
10,
12
],
[
1,
2,
7,
2,
6,
1,
15,
0
],
[
10,
2,
1,
13,
2,
26,
5,
11
],
[
4,
3,
20,
3,
9,
5,
14,
7
],
[
4,
1,
1,
5,
2,
16,
2,
10
]
]
},
"macro_roc_auc_ovr": 0.669002340507073
},
"delta_accuracy": 0.02525252525252525,
"delta_macro_f1": 0.031757913302798674
},
"no_epss": {
"n_features": 54,
"dropped_count": 3,
"metrics": {
"model": "xgboost_no_epss",
"accuracy": 0.2474747474747475,
"macro_f1": 0.2237319833172186,
"weighted_f1": 0.24186505327006125,
"per_class_f1": {
"auth_access_control": 0.17204301075268819,
"cryptographic_failure": 0.08,
"information_disclosure": 0.25,
"injection_family": 0.3089430894308943,
"logic_flaw": 0.11904761904761904,
"memory_corruption": 0.4050632911392405,
"misconfiguration": 0.25757575757575757,
"supply_chain_weakness": 0.19718309859154928
},
"confusion_matrix": {
"labels": [
"auth_access_control",
"cryptographic_failure",
"information_disclosure",
"injection_family",
"logic_flaw",
"memory_corruption",
"misconfiguration",
"supply_chain_weakness"
],
"matrix": [
[
8,
6,
0,
12,
7,
11,
5,
4
],
[
6,
3,
3,
5,
10,
4,
12,
2
],
[
2,
2,
7,
2,
3,
0,
7,
0
],
[
2,
5,
2,
19,
6,
20,
6,
5
],
[
2,
3,
5,
2,
5,
1,
15,
1
],
[
9,
6,
0,
10,
2,
32,
4,
7
],
[
6,
2,
16,
1,
15,
4,
17,
4
],
[
5,
3,
0,
7,
2,
16,
1,
7
]
]
},
"macro_roc_auc_ovr": 0.6925718594708064
},
"delta_accuracy": -0.01010101010101011,
"delta_macro_f1": 0.0006428454117919091
},
"no_flags": {
"n_features": 48,
"dropped_count": 9,
"metrics": {
"model": "xgboost_no_flags",
"accuracy": 0.22727272727272727,
"macro_f1": 0.21140688534448485,
"weighted_f1": 0.2214593080677342,
"per_class_f1": {
"auth_access_control": 0.13186813186813187,
"cryptographic_failure": 0.1686746987951807,
"information_disclosure": 0.3333333333333333,
"injection_family": 0.2764227642276423,
"logic_flaw": 0.08450704225352113,
"memory_corruption": 0.34838709677419355,
"misconfiguration": 0.24806201550387597,
"supply_chain_weakness": 0.1
},
"confusion_matrix": {
"labels": [
"auth_access_control",
"cryptographic_failure",
"information_disclosure",
"injection_family",
"logic_flaw",
"memory_corruption",
"misconfiguration",
"supply_chain_weakness"
],
"matrix": [
[
6,
6,
1,
9,
5,
10,
6,
10
],
[
5,
7,
3,
5,
5,
4,
14,
2
],
[
3,
0,
10,
1,
4,
0,
5,
0
],
[
3,
7,
1,
17,
7,
18,
4,
8
],
[
3,
5,
6,
2,
3,
2,
13,
0
],
[
8,
3,
0,
14,
3,
27,
4,
11
],
[
4,
10,
16,
2,
7,
6,
16,
4
],
[
6,
0,
0,
8,
3,
18,
2,
4
]
]
},
"macro_roc_auc_ovr": 0.6776398959263554
},
"delta_accuracy": 0.01010101010101011,
"delta_macro_f1": 0.01296794338452567
},
"no_asset": {
"n_features": 18,
"dropped_count": 39,
"metrics": {
"model": "xgboost_no_asset",
"accuracy": 0.21717171717171718,
"macro_f1": 0.19672873773465777,
"weighted_f1": 0.2140924517062793,
"per_class_f1": {
"auth_access_control": 0.10526315789473684,
"cryptographic_failure": 0.13043478260869565,
"information_disclosure": 0.13793103448275862,
"injection_family": 0.17857142857142858,
"logic_flaw": 0.08695652173913043,
"memory_corruption": 0.37333333333333335,
"misconfiguration": 0.26865671641791045,
"supply_chain_weakness": 0.2926829268292683
},
"confusion_matrix": {
"labels": [
"auth_access_control",
"cryptographic_failure",
"information_disclosure",
"injection_family",
"logic_flaw",
"memory_corruption",
"misconfiguration",
"supply_chain_weakness"
],
"matrix": [
[
5,
6,
1,
8,
5,
16,
7,
5
],
[
5,
6,
6,
5,
5,
3,
13,
2
],
[
2,
2,
4,
1,
4,
1,
8,
1
],
[
11,
7,
1,
10,
8,
15,
7,
6
],
[
1,
6,
8,
2,
3,
1,
12,
1
],
[
9,
9,
0,
9,
2,
28,
3,
10
],
[
4,
10,
15,
7,
5,
2,
18,
4
],
[
5,
1,
0,
5,
3,
14,
1,
12
]
]
},
"macro_roc_auc_ovr": 0.6869647093980484
},
"delta_accuracy": 0.020202020202020193,
"delta_macro_f1": 0.02764609099435275
},
"no_severity": {
"n_features": 53,
"dropped_count": 4,
"metrics": {
"model": "xgboost_no_severity",
"accuracy": 0.22727272727272727,
"macro_f1": 0.21747488568762768,
"weighted_f1": 0.2268764018926795,
"per_class_f1": {
"auth_access_control": 0.14893617021276595,
"cryptographic_failure": 0.19047619047619047,
"information_disclosure": 0.23333333333333334,
"injection_family": 0.288135593220339,
"logic_flaw": 0.12658227848101267,
"memory_corruption": 0.28205128205128205,
"misconfiguration": 0.24806201550387597,
"supply_chain_weakness": 0.2222222222222222
},
"confusion_matrix": {
"labels": [
"auth_access_control",
"cryptographic_failure",
"information_disclosure",
"injection_family",
"logic_flaw",
"memory_corruption",
"misconfiguration",
"supply_chain_weakness"
],
"matrix": [
[
7,
7,
0,
9,
7,
12,
7,
4
],
[
5,
8,
3,
2,
8,
5,
14,
0
],
[
3,
0,
7,
1,
7,
0,
5,
0
],
[
3,
6,
2,
17,
5,
20,
7,
5
],
[
3,
5,
7,
3,
5,
2,
9,
0
],
[
10,
7,
0,
13,
4,
22,
4,
10
],
[
5,
6,
18,
2,
8,
6,
16,
4
],
[
5,
0,
0,
6,
1,
19,
2,
8
]
]
},
"macro_roc_auc_ovr": 0.6857295225029008
},
"delta_accuracy": 0.01010101010101011,
"delta_macro_f1": 0.006899943041382833
},
"no_engineered": {
"n_features": 52,
"dropped_count": 5,
"metrics": {
"model": "xgboost_no_engineered",
"accuracy": 0.23232323232323232,
"macro_f1": 0.22158389829583944,
"weighted_f1": 0.22713804092389037,
"per_class_f1": {
"auth_access_control": 0.15053763440860216,
"cryptographic_failure": 0.14285714285714285,
"information_disclosure": 0.3157894736842105,
"injection_family": 0.23931623931623933,
"logic_flaw": 0.12987012987012986,
"memory_corruption": 0.345679012345679,
"misconfiguration": 0.23809523809523808,
"supply_chain_weakness": 0.21052631578947367
},
"confusion_matrix": {
"labels": [
"auth_access_control",
"cryptographic_failure",
"information_disclosure",
"injection_family",
"logic_flaw",
"memory_corruption",
"misconfiguration",
"supply_chain_weakness"
],
"matrix": [
[
7,
5,
0,
9,
9,
13,
6,
4
],
[
5,
6,
2,
3,
7,
4,
15,
3
],
[
3,
1,
9,
1,
6,
0,
3,
0
],
[
5,
8,
2,
14,
6,
19,
3,
8
],
[
2,
4,
4,
3,
5,
2,
14,
0
],
[
8,
6,
0,
13,
3,
28,
4,
8
],
[
5,
9,
17,
2,
6,
7,
15,
4
],
[
5,
0,
0,
7,
1,
19,
1,
8
]
]
},
"macro_roc_auc_ovr": 0.6871096699405611
},
"delta_accuracy": 0.005050505050505055,
"delta_macro_f1": 0.0027909304331710794
}
}
}