File size: 10,999 Bytes
16be928 | 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 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# CYB004 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 **phishing campaign phase** of a new per-timestep telemetry record.\n",
"\n",
"**Models predict one of 7 phases:** `target_reconnaissance`, `infrastructure_setup`, `lure_crafting`, `email_delivery`, `victim_engagement`, `credential_harvesting`, `post_compromise_escalation`.\n",
"\n",
"**This is a baseline reference model**, not a production email-security platform. See the model card for full metrics and limitations."
]
},
{
"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/cyb004-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, build_department_lookup\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": [
"# XGBoost\n",
"xgb_model = xgb.XGBClassifier()\n",
"xgb_model.load_model(files[\"model_xgb.json\"])\n",
"\n",
"# MLP architecture (must match training)\n",
"class PhaseMLP(nn.Module):\n",
" def __init__(self, n_features, n_classes=7, 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 = PhaseMLP(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. Build the department lookup\n",
"\n",
"Per-department topology features (employee_count, MFA enrollment, gateway architecture, DMARC level, etc.) are pulled from `victim_topology.csv` and merged into each timestep record by `target_department_id`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from huggingface_hub import snapshot_download\n",
"\n",
"ds_path = snapshot_download(repo_id=\"xpertsystems/cyb004-sample\", repo_type=\"dataset\")\n",
"\n",
"dept_lookup = build_department_lookup(\n",
" os.path.join(ds_path, \"victim_topology.csv\")\n",
")\n",
"print(f\"loaded {len(dept_lookup)} department profiles\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5. 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_phase(record: dict) -> dict:\n",
" \"\"\"Predict the campaign phase for one per-timestep telemetry record.\n",
"\n",
" Per-department topology features are pulled automatically via\n",
" `target_department_id` from the dept_lookup loaded above.\n",
" \"\"\"\n",
" dept_id = int(record.get(\"target_department_id\", -1))\n",
" dept_aggs = dept_lookup.get(dept_id, {})\n",
" X = transform_single(record, meta, victim_aggregates=dept_aggs)\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": [
"## 6. Run on an example record\n",
"\n",
"Real `email_delivery` event lifted from the sample dataset: a nation-state APT campaign at timestep 13, with homoglyph substitution evasion active and 58 emails sent. Both models should predict `email_delivery`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Real timestep record from the sample dataset (true phase: email_delivery)\n",
"example_record = {\n",
" \"timestep\": 13,\n",
" \"emails_sent_cumulative\": 58,\n",
" \"click_through_rate\": 0.1158,\n",
" \"credential_submission_rate\": 0.0713,\n",
" \"gateway_detection_score\": 0.7327,\n",
" \"lure_personalisation_score\": 0.7507,\n",
" \"evasion_technique_active\": \"homoglyph_substitution\",\n",
" \"target_department_id\": 10,\n",
" \"actor_capability_tier\": \"nation_state_apt\",\n",
"}\n",
"\n",
"result = predict_phase(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])[:5]:\n",
" print(f\" P({lbl:30s}) = {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])[:5]:\n",
" print(f\" P({lbl:30s}) = {p:.4f}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Note: when the two models disagree\n",
"\n",
"XGBoost and the MLP can disagree on mid-pipeline phases (`victim_engagement`, `credential_harvesting`) where timestep windows overlap. The per-class F1 in the model card identifies which phases are robustly predicted vs. which are not. In a SOC workflow, conflicting predictions are worth surfacing for human review."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 7. Batch prediction on the sample dataset"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"traj = pd.read_csv(f\"{ds_path}/campaign_trajectories.csv\")\n",
"\n",
"# Drop the leaky column the model was never trained on\n",
"traj = traj.drop(columns=[\"delivery_outcome\"], errors=\"ignore\")\n",
"\n",
"# Score the first 200 timesteps\n",
"sample = traj.head(200).copy()\n",
"preds = [predict_phase(row.to_dict())[\"xgboost\"][\"label\"] for _, row in sample.iterrows()]\n",
"sample[\"xgb_pred\"] = preds\n",
"\n",
"ct = pd.crosstab(sample[\"campaign_phase\"], sample[\"xgb_pred\"],\n",
" rownames=[\"true\"], colnames=[\"pred\"])\n",
"print(\"Confusion on first 200 sample rows (XGBoost):\")\n",
"print(ct)\n",
"acc = (sample[\"campaign_phase\"] == sample[\"xgb_pred\"]).mean()\n",
"print(f\"\\nbatch accuracy on first 200 rows (in-distribution): {acc:.4f}\")\n",
"print(\"\\nNote: these rows include training-set campaigns. See validation_results.json\\n\"\n",
" \"for proper held-out test metrics from disjoint campaigns.\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 8. Next steps\n",
"\n",
"- See `validation_results.json` for held-out test metrics (15 disjoint campaigns, ~580 timesteps).\n",
"- See `multi_seed_results.json` for the across-10-seeds robustness picture (accuracy 0.649 ± 0.038, ROC-AUC 0.937 ± 0.010).\n",
"- See `ablation_results.json` for per-feature-group contribution. `timestep` carries the dominant signal.\n",
"- The model card explains why `actor_capability_tier` was *not* used as the target despite being the README's headline use case.\n",
"- For the full 335k-row CYB004 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
}
|