orgforge-it / insider_threat_leaderboard.json
jflynt's picture
Upload folder using huggingface_hub
f17ff41 verified
[
{
"run_id": "mistral.devstral-2-123b__20260320T171503",
"timestamp": "2026-03-20T22:27:39.006654+00:00",
"model": "mistral.devstral-2-123b",
"tier": "2",
"sim_days": 51,
"subjects": 3,
"subject_classes": [],
"triage_precision": 0.6667,
"triage_recall": 1.0,
"triage_f1": 0.8,
"triage_tp": 2,
"triage_fp": 1,
"triage_fn": 0,
"baseline_fp_rate": 0.0208,
"onset_sensitivity": 0.0,
"verdict_precision": 1.0,
"verdict_recall": 1.0,
"verdict_f1": 1.0,
"verdict_tp": 2,
"verdict_fp": 0,
"verdict_fn": 0,
"vishing_detected": true,
"host_trail_reconstructed": true,
"by_behavior": {
"unusual_hours_access": {
"tp": 2,
"fp": 0
},
"sentiment_drift": {
"tp": 2,
"fp": 0
},
"host_data_hoarding": {
"tp": 1,
"fp": 0
},
"data_exfil_email": {
"tp": 1,
"fp": 0
},
"social_engineering": {
"tp": 1,
"fp": 0
},
"idp_anomaly": {
"tp": 0,
"fp": 2
}
},
"by_class": {
"malicious": {
"tp": 1,
"fp": 0,
"fn": 0
},
"disgruntled": {
"tp": 1,
"fp": 0,
"fn": 0
}
}
},
{
"run_id": "us.anthropic.claude-opus-4-6-v1__20260320T184150",
"timestamp": "2026-03-20T23:47:13.003756+00:00",
"model": "us.anthropic.claude-opus-4-6-v1",
"tier": "2",
"sim_days": 51,
"subjects": 3,
"subject_classes": [],
"triage_precision": 0.6667,
"triage_recall": 1.0,
"triage_f1": 0.8,
"triage_tp": 2,
"triage_fp": 1,
"triage_fn": 0,
"baseline_fp_rate": 0.0208,
"onset_sensitivity": 0.0,
"verdict_precision": 1.0,
"verdict_recall": 1.0,
"verdict_f1": 1.0,
"verdict_tp": 2,
"verdict_fp": 0,
"verdict_fn": 0,
"vishing_detected": true,
"host_trail_reconstructed": true,
"by_behavior": {
"host_data_hoarding": {
"tp": 1,
"fp": 0
},
"data_exfil_email": {
"tp": 1,
"fp": 0
},
"social_engineering": {
"tp": 1,
"fp": 0
},
"sentiment_drift": {
"tp": 2,
"fp": 0
},
"unusual_hours_access": {
"tp": 2,
"fp": 0
},
"idp_anomaly": {
"tp": 0,
"fp": 2
}
},
"by_class": {
"malicious": {
"tp": 1,
"fp": 0,
"fn": 0
},
"disgruntled": {
"tp": 1,
"fp": 0,
"fn": 0
}
}
},
{
"run_id": "deepseek.v3.2__20260320T190338",
"timestamp": "2026-03-21T00:12:56.410476+00:00",
"model": "deepseek.v3.2",
"tier": "2",
"sim_days": 51,
"subjects": 3,
"subject_classes": [],
"triage_precision": 0.6667,
"triage_recall": 1.0,
"triage_f1": 0.8,
"triage_tp": 2,
"triage_fp": 1,
"triage_fn": 0,
"baseline_fp_rate": 0.0208,
"onset_sensitivity": 0.0,
"verdict_precision": 0.6667,
"verdict_recall": 1.0,
"verdict_f1": 0.8,
"verdict_tp": 2,
"verdict_fp": 1,
"verdict_fn": 0,
"vishing_detected": true,
"host_trail_reconstructed": true,
"by_behavior": {
"host_data_hoarding": {
"tp": 1,
"fp": 0
},
"data_exfil_email": {
"tp": 1,
"fp": 0
},
"social_engineering": {
"tp": 1,
"fp": 0
},
"unusual_hours_access": {
"tp": 2,
"fp": 0
},
"sentiment_drift": {
"tp": 2,
"fp": 0
},
"idp_anomaly": {
"tp": 0,
"fp": 2
}
},
"by_class": {
"innocent": {
"tp": 0,
"fp": 1,
"fn": 0
},
"malicious": {
"tp": 1,
"fp": 0,
"fn": 0
},
"disgruntled": {
"tp": 1,
"fp": 0,
"fn": 0
}
}
},
{
"run_id": "us.meta.llama3-3-70b-instruct-v1_0__20260320T173939",
"timestamp": "2026-03-20T22:46:04.844221+00:00",
"model": "us.meta.llama3-3-70b-instruct-v1:0",
"tier": "2",
"sim_days": 51,
"subjects": 3,
"subject_classes": [],
"triage_precision": 0.0488,
"triage_recall": 1.0,
"triage_f1": 0.093,
"triage_tp": 2,
"triage_fp": 39,
"triage_fn": 0,
"baseline_fp_rate": 0.8125,
"onset_sensitivity": 0.0,
"verdict_precision": 0.6667,
"verdict_recall": 1.0,
"verdict_f1": 0.8,
"verdict_tp": 2,
"verdict_fp": 1,
"verdict_fn": 0,
"vishing_detected": true,
"host_trail_reconstructed": true,
"by_behavior": {
"unusual_hours_access": {
"tp": 2,
"fp": 0
},
"excessive_repo_cloning": {
"tp": 0,
"fp": 1
},
"sentiment_drift": {
"tp": 2,
"fp": 0
},
"cross_dept_snooping": {
"tp": 0,
"fp": 1
},
"data_exfil_email": {
"tp": 1,
"fp": 0
},
"host_data_hoarding": {
"tp": 1,
"fp": 0
},
"social_engineering": {
"tp": 1,
"fp": 0
},
"idp_anomaly": {
"tp": 0,
"fp": 1
}
},
"by_class": {
"innocent": {
"tp": 0,
"fp": 1,
"fn": 0
},
"malicious": {
"tp": 1,
"fp": 0,
"fn": 0
},
"disgruntled": {
"tp": 1,
"fp": 0,
"fn": 0
}
}
},
{
"run_id": "us.anthropic.claude-sonnet-4-6__20260320T180625",
"timestamp": "2026-03-20T23:11:46.096659+00:00",
"model": "us.anthropic.claude-sonnet-4-6",
"tier": "2",
"sim_days": 51,
"subjects": 3,
"subject_classes": [],
"triage_precision": 0.6667,
"triage_recall": 1.0,
"triage_f1": 0.8,
"triage_tp": 2,
"triage_fp": 1,
"triage_fn": 0,
"baseline_fp_rate": 0.0208,
"onset_sensitivity": 0.0,
"verdict_precision": 0.0,
"verdict_recall": 0.0,
"verdict_f1": 0.0,
"verdict_tp": 0,
"verdict_fp": 1,
"verdict_fn": 2,
"vishing_detected": true,
"host_trail_reconstructed": false,
"by_behavior": {},
"by_class": {
"innocent": {
"tp": 0,
"fp": 1,
"fn": 0
},
"disgruntled": {
"tp": 0,
"fp": 0,
"fn": 1
},
"malicious": {
"tp": 0,
"fp": 0,
"fn": 1
}
}
},
{
"run_id": "us.anthropic.claude-haiku-4-5-20251001-v1_0__20260320T173444",
"timestamp": "2026-03-20T22:36:32.924907+00:00",
"model": "us.anthropic.claude-haiku-4-5-20251001-v1:0",
"tier": "2",
"sim_days": 51,
"subjects": 3,
"subject_classes": [],
"triage_precision": 0.6667,
"triage_recall": 1.0,
"triage_f1": 0.8,
"triage_tp": 2,
"triage_fp": 1,
"triage_fn": 0,
"baseline_fp_rate": 0.0213,
"onset_sensitivity": 0.0,
"verdict_precision": 0.0,
"verdict_recall": 0.0,
"verdict_f1": 0.0,
"verdict_tp": 0,
"verdict_fp": 1,
"verdict_fn": 2,
"vishing_detected": true,
"host_trail_reconstructed": false,
"by_behavior": {},
"by_class": {
"innocent": {
"tp": 0,
"fp": 1,
"fn": 0
},
"disgruntled": {
"tp": 0,
"fp": 0,
"fn": 1
},
"malicious": {
"tp": 0,
"fp": 0,
"fn": 1
}
}
}
]