File size: 11,782 Bytes
e6a6835
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# CYB006 Baseline Classifier — Inference Example\n",
    "\n",
    "End-to-end demo: load the trained XGBoost and PyTorch MLP models from the Hugging Face repo and predict the **user risk tier** (`low` / `medium` / `high`) of an identity from per-user aggregates joined with non-leaky session aggregates.\n",
    "\n",
    "**This is a baseline reference model**, not a production identity-security platform. See the model card for full metrics and limitations — and importantly, see the **`leakage_diagnostic.json`** for why this baseline targets `user_risk_tier` rather than the README's stated headline use case of threat-actor tier attribution."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. Install dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install --quiet xgboost torch safetensors pandas numpy huggingface_hub"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Download model artifacts from Hugging Face"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from huggingface_hub import hf_hub_download\n",
    "\n",
    "REPO_ID = \"xpertsystems/cyb006-baseline-classifier\"\n",
    "\n",
    "files = {}\n",
    "for name in [\"model_xgb.json\", \"model_mlp.safetensors\",\n",
    "             \"feature_engineering.py\", \"feature_meta.json\",\n",
    "             \"feature_scaler.json\"]:\n",
    "    files[name] = hf_hub_download(repo_id=REPO_ID, filename=name)\n",
    "    print(f\"  downloaded: {name}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys, os\n",
    "fe_dir = os.path.dirname(files[\"feature_engineering.py\"])\n",
    "if fe_dir not in sys.path:\n",
    "    sys.path.insert(0, fe_dir)\n",
    "\n",
    "from feature_engineering import (\n",
    "    transform_single, load_meta, INT_TO_LABEL,\n",
    "    compute_session_aggregates_for_user\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3. Load models and metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import numpy as np\n",
    "import torch\n",
    "import torch.nn as nn\n",
    "import xgboost as xgb\n",
    "from safetensors.torch import load_file\n",
    "\n",
    "meta = load_meta(files[\"feature_meta.json\"])\n",
    "with open(files[\"feature_scaler.json\"]) as f:\n",
    "    scaler = json.load(f)\n",
    "\n",
    "N_FEATURES = len(meta[\"feature_names\"])\n",
    "N_CLASSES = len(meta[\"int_to_label\"])\n",
    "print(f\"feature count: {N_FEATURES}\")\n",
    "print(f\"class count:   {N_CLASSES}\")\n",
    "print(f\"label classes: {list(meta['int_to_label'].values())}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "xgb_model = xgb.XGBClassifier()\n",
    "xgb_model.load_model(files[\"model_xgb.json\"])\n",
    "\n",
    "# MLP architecture (must match training)\n",
    "class RiskTierMLP(nn.Module):\n",
    "    def __init__(self, n_features, n_classes=3, hidden1=128, hidden2=64, dropout=0.3):\n",
    "        super().__init__()\n",
    "        self.net = nn.Sequential(\n",
    "            nn.Linear(n_features, hidden1),\n",
    "            nn.BatchNorm1d(hidden1),\n",
    "            nn.ReLU(),\n",
    "            nn.Dropout(dropout),\n",
    "            nn.Linear(hidden1, hidden2),\n",
    "            nn.BatchNorm1d(hidden2),\n",
    "            nn.ReLU(),\n",
    "            nn.Dropout(dropout),\n",
    "            nn.Linear(hidden2, n_classes),\n",
    "        )\n",
    "    def forward(self, x):\n",
    "        return self.net(x)\n",
    "\n",
    "mlp_model = RiskTierMLP(N_FEATURES, n_classes=N_CLASSES)\n",
    "mlp_model.load_state_dict(load_file(files[\"model_mlp.safetensors\"]))\n",
    "mlp_model.eval()\n",
    "print(\"models loaded\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Prediction helper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "MU = np.array(scaler[\"mean\"], dtype=np.float32)\n",
    "SD = np.array(scaler[\"std\"],  dtype=np.float32)\n",
    "\n",
    "def predict_risk_tier(user_record: dict) -> dict:\n",
    "    \"\"\"Predict the user risk tier from a per-user record.\n",
    "\n",
    "    The record should contain per-user aggregates (from user_risk_summary)\n",
    "    PLUS the session aggregates produced by compute_session_aggregates_for_user.\n",
    "    See the example record below.\n",
    "    \"\"\"\n",
    "    X = transform_single(user_record, meta)\n",
    "\n",
    "    xgb_proba = xgb_model.predict_proba(X)[0]\n",
    "    xgb_label = INT_TO_LABEL[int(np.argmax(xgb_proba))]\n",
    "\n",
    "    Xs = ((X - MU) / SD).astype(np.float32)\n",
    "    with torch.no_grad():\n",
    "        logits = mlp_model(torch.tensor(Xs))\n",
    "        mlp_proba = torch.softmax(logits, dim=1).numpy()[0]\n",
    "    mlp_label = INT_TO_LABEL[int(np.argmax(mlp_proba))]\n",
    "\n",
    "    return {\n",
    "        \"xgboost\": {\n",
    "            \"label\": xgb_label,\n",
    "            \"probabilities\": {INT_TO_LABEL[i]: float(p) for i, p in enumerate(xgb_proba)},\n",
    "        },\n",
    "        \"mlp\": {\n",
    "            \"label\": mlp_label,\n",
    "            \"probabilities\": {INT_TO_LABEL[i]: float(p) for i, p in enumerate(mlp_proba)},\n",
    "        },\n",
    "    }"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 5. Run on an example record\n",
    "\n",
    "Real high-risk user from the sample dataset: 98 login attempts in window, 25 failures, 9 account lockouts, 9 impossible-travel events, 6 unique countries, peak privilege `admin_domain`. Both models should predict `high`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Real per-user record from the sample dataset (true tier: high)\n",
    "example_record = {\n",
    "    # Per-user aggregates (from user_risk_summary.csv)\n",
    "    \"total_login_attempts\": 98,\n",
    "    \"successful_logins\": 0,\n",
    "    \"failed_logins\": 25,\n",
    "    \"mfa_failures\": 0,\n",
    "    \"impossible_travel_events\": 9,\n",
    "    \"lateral_hop_count\": 1,\n",
    "    \"privilege_escalations\": 1,\n",
    "    \"account_lockout_count\": 9,\n",
    "    \"geo_dispersion_score\": 0.6474,\n",
    "    \"login_velocity_score\": 0.6387,\n",
    "    \"session_anomaly_rate\": 1.0,\n",
    "    \"ueba_alert_count\": 0,\n",
    "    \"overall_identity_risk_score\": 0.3452,\n",
    "    \"peak_privilege_level_accessed\": \"admin_domain\",\n",
    "    \"insider_threat_indicator_score\": 0.0,\n",
    "    # Session aggregates (computed via compute_session_aggregates_for_user)\n",
    "    \"avg_session_duration_seconds\": 352.24,\n",
    "    \"avg_mfa_response_latency_ms\": 26.67,\n",
    "    \"avg_geo_anomaly_score\": 0.6474,\n",
    "    \"max_geo_anomaly_score\": 1.0,\n",
    "    \"frac_impossible_travel\": 0.36,\n",
    "    \"n_unique_countries\": 6,\n",
    "    \"n_unique_devices\": 25,\n",
    "    \"n_unique_applications\": 1,\n",
    "}\n",
    "\n",
    "result = predict_risk_tier(example_record)\n",
    "\n",
    "print(f\"XGBoost  ->  {result['xgboost']['label']}\")\n",
    "for lbl, p in sorted(result['xgboost']['probabilities'].items(), key=lambda x: -x[1]):\n",
    "    print(f\"    P({lbl:8s}) = {p:.4f}\")\n",
    "\n",
    "print(f\"\\nMLP      ->  {result['mlp']['label']}\")\n",
    "for lbl, p in sorted(result['mlp']['probabilities'].items(), key=lambda x: -x[1]):\n",
    "    print(f\"    P({lbl:8s}) = {p:.4f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 6. Batch prediction on the sample dataset\n",
    "\n",
    "Score every user in `user_risk_summary.csv` after joining their session aggregates from `login_sessions.csv`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from huggingface_hub import snapshot_download\n",
    "import pandas as pd\n",
    "\n",
    "ds_path = snapshot_download(repo_id=\"xpertsystems/cyb006-sample\", repo_type=\"dataset\")\n",
    "users = pd.read_csv(f\"{ds_path}/user_risk_summary.csv\")\n",
    "sessions = pd.read_csv(f\"{ds_path}/login_sessions.csv\")\n",
    "\n",
    "preds = []\n",
    "for _, row in users.head(50).iterrows():\n",
    "    user_sessions = sessions[sessions[\"user_id\"] == row[\"user_id\"]]\n",
    "    if len(user_sessions) == 0:\n",
    "        continue\n",
    "    rec = row.to_dict()\n",
    "    rec.update(compute_session_aggregates_for_user(user_sessions))\n",
    "    pred = predict_risk_tier(rec)\n",
    "    preds.append({\n",
    "        \"user_id\": row[\"user_id\"],\n",
    "        \"true_tier\": row[\"user_risk_tier\"],\n",
    "        \"xgb_pred\": pred[\"xgboost\"][\"label\"],\n",
    "    })\n",
    "\n",
    "results = pd.DataFrame(preds)\n",
    "ct = pd.crosstab(results[\"true_tier\"], results[\"xgb_pred\"],\n",
    "                 rownames=[\"true\"], colnames=[\"pred\"])\n",
    "print(\"Confusion on first 50 users (XGBoost):\")\n",
    "print(ct)\n",
    "acc = (results[\"true_tier\"] == results[\"xgb_pred\"]).mean()\n",
    "print(f\"\\nbatch accuracy on first 50 users (in-distribution): {acc:.4f}\")\n",
    "print(\"\\nNote: this includes training-set users. See validation_results.json\\n\"\n",
    "      \"for proper held-out test metrics.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 7. Important: the leakage diagnostic\n",
    "\n",
    "Before using CYB006 sample data to train a threat-actor detector, read **`leakage_diagnostic.json`** in this repo. The README's stated headline use case (4-class threat-actor tier attribution) is not a representative ML task on the sample dataset — the synthetic generator produces threat-actor sessions with non-overlapping anomaly score distributions, so a plain XGBoost achieves 100% accuracy that doesn't reflect any real learning. The diagnostic documents which feature groups carry the leakage and what we recommend to dataset authors.\n",
    "\n",
    "This baseline ships `user_risk_tier` prediction instead, which has overlapping per-tier distributions and lifts ~10pp over majority baseline."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 8. Next steps\n",
    "\n",
    "- See `validation_results.json` for held-out test metrics (30 disjoint users).\n",
    "- See `multi_seed_results.json` for the across-10-seeds picture (accuracy 0.700 ± 0.082, ROC-AUC 0.812 ± 0.048).\n",
    "- See `ablation_results.json` for per-feature-group contribution. User aggregate counts (failed logins, lateral hops, etc.) carry the most signal.\n",
    "- See **`leakage_diagnostic.json`** for the detailed audit on threat-actor detection.\n",
    "- For the full ~1.1M-row CYB006 dataset and commercial licensing, contact **pradeep@xpertsystems.ai**."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}