File size: 38,116 Bytes
9ff5b8d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 |
{
"cells": [
{
"cell_type": "markdown",
"id": "0d580912",
"metadata": {},
"source": [
"# 🧠 Deep Learning Security Models\n",
"\n",
"## Advanced Neural Networks for Cybersecurity\n",
"\n",
"This notebook focuses on training **deep learning models** for security classification:\n",
"\n",
"- **Transformer-based Detection** - Attention mechanisms for sequence analysis\n",
"- **Convolutional Networks** - Pattern detection in security data\n",
"- **LSTM/GRU Networks** - Temporal pattern recognition\n",
"- **AutoEncoders** - Anomaly detection via reconstruction error\n",
"- **Multi-Task Learning** - Unified model for multiple security domains"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "2a6ddc2d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"🐍 Current Python: 3.15.0a3 (v3.15.0a3:f1eb0c0b0cd, Dec 16 2025, 08:05:19) [Clang 17.0.0 (clang-1700.6.3.2)]\n",
"⚠️ Python 3.15 detected. TensorFlow requires Python 3.9-3.11\n",
" Installing other packages without TensorFlow...\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n",
" \n",
" \u001b[31m×\u001b[0m \u001b[32minstalling build dependencies for scikit-learn\u001b[0m did not run successfully.\n",
" \u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n",
" \u001b[31m╰─>\u001b[0m \u001b[31m[81 lines of output]\u001b[0m\n",
" \u001b[31m \u001b[0m Collecting meson-python<0.19.0,>=0.17.1\n",
" \u001b[31m \u001b[0m Using cached meson_python-0.18.0-py3-none-any.whl.metadata (2.8 kB)\n",
" \u001b[31m \u001b[0m Collecting cython<3.3.0,>=3.1.2\n",
" \u001b[31m \u001b[0m Using cached cython-3.2.4-cp39-abi3-macosx_10_9_x86_64.whl.metadata (7.5 kB)\n",
" \u001b[31m \u001b[0m Collecting numpy<2.4.0,>=2\n",
" \u001b[31m \u001b[0m Using cached numpy-2.3.5.tar.gz (20.6 MB)\n",
" \u001b[31m \u001b[0m Installing build dependencies: started\n",
" \u001b[31m \u001b[0m Installing build dependencies: finished with status 'done'\n",
" \u001b[31m \u001b[0m Getting requirements to build wheel: started\n",
" \u001b[31m \u001b[0m Getting requirements to build wheel: finished with status 'done'\n",
" \u001b[31m \u001b[0m Installing backend dependencies: started\n",
" \u001b[31m \u001b[0m Installing backend dependencies: finished with status 'done'\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): started\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): still running...\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): finished with status 'done'\n",
" \u001b[31m \u001b[0m \u001b[33mWARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProtocolError('Connection aborted.', ConnectionResetError(54, 'Connection reset by peer'))': /simple/scipy/\u001b[0m\u001b[33m\n",
" \u001b[31m \u001b[0m \u001b[0mCollecting scipy<1.17.0,>=1.10.0\n",
" \u001b[31m \u001b[0m Using cached scipy-1.16.3.tar.gz (30.6 MB)\n",
" \u001b[31m \u001b[0m Installing build dependencies: started\n",
" \u001b[31m \u001b[0m Installing build dependencies: finished with status 'done'\n",
" \u001b[31m \u001b[0m Getting requirements to build wheel: started\n",
" \u001b[31m \u001b[0m Getting requirements to build wheel: finished with status 'done'\n",
" \u001b[31m \u001b[0m Installing backend dependencies: started\n",
" \u001b[31m \u001b[0m Installing backend dependencies: finished with status 'done'\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): started\n",
" \u001b[31m \u001b[0m Preparing metadata (pyproject.toml): finished with status 'error'\n",
" \u001b[31m \u001b[0m \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m \u001b[31m×\u001b[0m \u001b[32mPreparing metadata \u001b[0m\u001b[1;32m(\u001b[0m\u001b[32mpyproject.toml\u001b[0m\u001b[1;32m)\u001b[0m did not run successfully.\n",
" \u001b[31m \u001b[0m \u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n",
" \u001b[31m \u001b[0m \u001b[31m╰─>\u001b[0m \u001b[31m[23 lines of output]\u001b[0m\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m \u001b[36m\u001b[1m+ meson setup /private/var/folders/3f/7mz66tl156s4w_xt0pqq7bwc0000gn/T/pip-install-iutka178/scipy_bdc2fda37451456fa9ccb51189c51876 /private/var/folders/3f/7mz66tl156s4w_xt0pqq7bwc0000gn/T/pip-install-iutka178/scipy_bdc2fda37451456fa9ccb51189c51876/.mesonpy-3_laly6u -Dbuildtype=release -Db_ndebug=if-release -Db_vscrt=md --native-file=/private/var/folders/3f/7mz66tl156s4w_xt0pqq7bwc0000gn/T/pip-install-iutka178/scipy_bdc2fda37451456fa9ccb51189c51876/.mesonpy-3_laly6u/meson-python-native-file.ini\u001b[0m\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m The Meson build system\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Version: 1.10.1\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Source dir: /private/var/folders/3f/7mz66tl156s4w_xt0pqq7bwc0000gn/T/pip-install-iutka178/scipy_bdc2fda37451456fa9ccb51189c51876\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Build dir: /private/var/folders/3f/7mz66tl156s4w_xt0pqq7bwc0000gn/T/pip-install-iutka178/scipy_bdc2fda37451456fa9ccb51189c51876/.mesonpy-3_laly6u\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Build type: native build\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Project name: scipy\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Project version: 1.16.3\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m C compiler for the host machine: cc (clang 14.0.3 \"Apple clang version 14.0.3 (clang-1403.0.22.14.1)\")\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m C linker for the host machine: cc ld64 857.1\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m C++ compiler for the host machine: c++ (clang 14.0.3 \"Apple clang version 14.0.3 (clang-1403.0.22.14.1)\")\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m C++ linker for the host machine: c++ ld64 857.1\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Cython compiler for the host machine: cython (cython 3.1.8)\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Host machine cpu family: x86_64\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Host machine cpu: x86_64\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Program python found: YES (/Users/Dadaicon/Documents/GitHub/Real-Time-cyber-Forge-Agentic-AI/.venv/bin/python)\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Found pkg-config: YES (/usr/local/bin/pkg-config) 2.5.1\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Run-time dependency python found: YES 3.15\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m Program cython found: YES (/private/var/folders/3f/7mz66tl156s4w_xt0pqq7bwc0000gn/T/pip-build-env-dno50jhk/overlay/bin/cython)\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m ../meson.build:53:4: ERROR: Problem encountered: SciPy requires clang >= 15.0\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m A full log can be found at /private/var/folders/3f/7mz66tl156s4w_xt0pqq7bwc0000gn/T/pip-install-iutka178/scipy_bdc2fda37451456fa9ccb51189c51876/.mesonpy-3_laly6u/meson-logs/meson-log.txt\n",
" \u001b[31m \u001b[0m \u001b[31m \u001b[0m \u001b[31m[end of output]\u001b[0m\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n",
" \u001b[31m \u001b[0m \u001b[1;31merror\u001b[0m: \u001b[1mmetadata-generation-failed\u001b[0m\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m \u001b[31m×\u001b[0m Encountered error while generating package metadata.\n",
" \u001b[31m \u001b[0m \u001b[31m╰─>\u001b[0m scipy\n",
" \u001b[31m \u001b[0m \n",
" \u001b[31m \u001b[0m \u001b[1;35mnote\u001b[0m: This is an issue with the package mentioned above, not pip.\n",
" \u001b[31m \u001b[0m \u001b[1;36mhint\u001b[0m: See above for details.\n",
" \u001b[31m \u001b[0m \u001b[31m[end of output]\u001b[0m\n",
" \n",
" \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n",
"\u001b[31mERROR: Failed to build 'scikit-learn' when installing build dependencies for scikit-learn\u001b[0m\u001b[31m\n",
"\u001b[0mNote: you may need to restart the kernel to use updated packages.\n",
"✅ Packages installed (without TensorFlow)\n",
" Please switch to Python 3.9-3.11 kernel to use deep learning models\n"
]
}
],
"source": [
"# Install required packages using pip magic (ensures correct kernel environment)\n",
"# Note: TensorFlow requires Python 3.9-3.11. If you see errors, switch to venv kernel or use Python 3.11\n",
"\n",
"import sys\n",
"print(f'🐍 Current Python: {sys.version}')\n",
"\n",
"# Check Python version\n",
"major, minor = sys.version_info[:2]\n",
"if major == 3 and 9 <= minor <= 11:\n",
" %pip install -q tensorflow scikit-learn pandas numpy matplotlib seaborn imbalanced-learn nest_asyncio tqdm\n",
" print('✅ All packages installed including TensorFlow')\n",
"else:\n",
" print(f'⚠️ Python {major}.{minor} detected. TensorFlow requires Python 3.9-3.11')\n",
" print(' Installing other packages without TensorFlow...')\n",
" %pip install -q scikit-learn pandas numpy matplotlib seaborn imbalanced-learn nest_asyncio tqdm\n",
" print('✅ Packages installed (without TensorFlow)')\n",
" print(' Please switch to Python 3.9-3.11 kernel to use deep learning models')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "f1af9c6b",
"metadata": {},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'matplotlib'",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mModuleNotFoundError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[3]\u001b[39m\u001b[32m, line 7\u001b[39m\n\u001b[32m 5\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mnumpy\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mnp\u001b[39;00m\n\u001b[32m 6\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpandas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpd\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m7\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmatplotlib\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mpyplot\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mplt\u001b[39;00m\n\u001b[32m 8\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mseaborn\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01msns\u001b[39;00m\n\u001b[32m 9\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpathlib\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m Path\n",
"\u001b[31mModuleNotFoundError\u001b[39m: No module named 'matplotlib'"
]
}
],
"source": [
"import os\n",
"import sys\n",
"import asyncio\n",
"import warnings\n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from pathlib import Path\n",
"from datetime import datetime\n",
"import json\n",
"import joblib\n",
"\n",
"# ML\n",
"from sklearn.model_selection import train_test_split, StratifiedKFold\n",
"from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
"from sklearn.metrics import (\n",
" classification_report, confusion_matrix, roc_auc_score,\n",
" roc_curve, precision_recall_curve, f1_score, accuracy_score\n",
")\n",
"\n",
"# Deep Learning\n",
"import tensorflow as tf\n",
"from tensorflow.keras.models import Model, Sequential\n",
"from tensorflow.keras.layers import (\n",
" Input, Dense, Dropout, BatchNormalization, \n",
" Conv1D, MaxPooling1D, GlobalMaxPooling1D, Flatten,\n",
" LSTM, GRU, Bidirectional, Attention, MultiHeadAttention,\n",
" Concatenate, Add, LayerNormalization, Embedding\n",
")\n",
"from tensorflow.keras.optimizers import Adam, AdamW\n",
"from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\n",
"from tensorflow.keras.regularizers import l1_l2\n",
"\n",
"from imblearn.over_sampling import SMOTE\n",
"\n",
"# Config\n",
"warnings.filterwarnings('ignore')\n",
"os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'\n",
"np.random.seed(42)\n",
"tf.random.set_seed(42)\n",
"\n",
"# Add path\n",
"sys.path.insert(0, str(Path.cwd().parent / 'app' / 'services'))\n",
"\n",
"try:\n",
" import nest_asyncio\n",
" nest_asyncio.apply()\n",
"except:\n",
" pass\n",
"\n",
"plt.style.use('dark_background')\n",
"\n",
"print('🚀 Environment ready!')\n",
"print(f' TensorFlow: {tf.__version__}')\n",
"print(f' GPU available: {len(tf.config.list_physical_devices(\"GPU\")) > 0}')"
]
},
{
"cell_type": "markdown",
"id": "7962e94f",
"metadata": {},
"source": [
"## 📥 Load Security Datasets"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "65ed96aa",
"metadata": {},
"outputs": [],
"source": [
"from web_security_datasets import WebSecurityDatasetManager\n",
"\n",
"DATASET_DIR = Path.cwd().parent / 'datasets' / 'web_security'\n",
"manager = WebSecurityDatasetManager(str(DATASET_DIR))\n",
"\n",
"# Download if needed\n",
"async def ensure_datasets():\n",
" if len(manager.downloaded_datasets) < 5:\n",
" print('📥 Downloading datasets...')\n",
" await manager.download_all_datasets()\n",
" return manager.downloaded_datasets\n",
"\n",
"datasets = asyncio.run(ensure_datasets())\n",
"print(f'\\n✅ {len(datasets)} datasets available')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "369d8983",
"metadata": {},
"outputs": [],
"source": [
"# Load combined dataset for multi-domain training\n",
"async def load_combined(max_per_ds: int = 20000):\n",
" return await manager.get_combined_dataset(max_samples_per_dataset=max_per_ds)\n",
"\n",
"combined_df = asyncio.run(load_combined())\n",
"print(f'📊 Combined dataset: {len(combined_df):,} samples')\n",
"print(f' Features: {combined_df.shape[1]}')\n",
"print(f' Categories: {combined_df[\"_category\"].value_counts().to_dict()}')"
]
},
{
"cell_type": "markdown",
"id": "3fc0c63d",
"metadata": {},
"source": [
"## 🏗️ Deep Learning Architectures"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f834f8a9",
"metadata": {},
"outputs": [],
"source": [
"class DeepSecurityModels:\n",
" \"\"\"Advanced deep learning models for security classification.\"\"\"\n",
" \n",
" @staticmethod\n",
" def transformer_block(x, embed_dim, num_heads, ff_dim, dropout=0.1):\n",
" \"\"\"Transformer encoder block.\"\"\"\n",
" # Multi-head attention\n",
" attn_output = MultiHeadAttention(\n",
" key_dim=embed_dim, num_heads=num_heads, dropout=dropout\n",
" )(x, x)\n",
" x1 = LayerNormalization(epsilon=1e-6)(x + attn_output)\n",
" \n",
" # Feed-forward\n",
" ff = Dense(ff_dim, activation='relu')(x1)\n",
" ff = Dropout(dropout)(ff)\n",
" ff = Dense(embed_dim)(ff)\n",
" return LayerNormalization(epsilon=1e-6)(x1 + ff)\n",
" \n",
" @staticmethod\n",
" def create_transformer_classifier(input_dim: int, \n",
" embed_dim: int = 64,\n",
" num_heads: int = 4,\n",
" ff_dim: int = 128,\n",
" num_blocks: int = 2) -> Model:\n",
" \"\"\"Transformer-based security classifier.\"\"\"\n",
" inputs = Input(shape=(input_dim,))\n",
" \n",
" # Project to embedding dimension\n",
" x = Dense(embed_dim)(inputs)\n",
" x = tf.expand_dims(x, axis=1) # Add sequence dimension\n",
" \n",
" # Stack transformer blocks\n",
" for _ in range(num_blocks):\n",
" x = DeepSecurityModels.transformer_block(x, embed_dim, num_heads, ff_dim)\n",
" \n",
" # Global pooling and classification\n",
" x = tf.squeeze(x, axis=1)\n",
" x = Dropout(0.2)(x)\n",
" x = Dense(32, activation='relu')(x)\n",
" outputs = Dense(1, activation='sigmoid')(x)\n",
" \n",
" model = Model(inputs, outputs, name='transformer_classifier')\n",
" model.compile(\n",
" optimizer=AdamW(learning_rate=1e-4),\n",
" loss='binary_crossentropy',\n",
" metrics=['accuracy', 'AUC']\n",
" )\n",
" return model\n",
" \n",
" @staticmethod\n",
" def create_cnn_classifier(input_dim: int) -> Model:\n",
" \"\"\"1D CNN for security pattern detection.\"\"\"\n",
" inputs = Input(shape=(input_dim, 1))\n",
" \n",
" # Conv blocks\n",
" x = Conv1D(64, 3, activation='relu', padding='same')(inputs)\n",
" x = BatchNormalization()(x)\n",
" x = MaxPooling1D(2)(x)\n",
" \n",
" x = Conv1D(128, 3, activation='relu', padding='same')(x)\n",
" x = BatchNormalization()(x)\n",
" x = MaxPooling1D(2)(x)\n",
" \n",
" x = Conv1D(256, 3, activation='relu', padding='same')(x)\n",
" x = GlobalMaxPooling1D()(x)\n",
" \n",
" # Classification head\n",
" x = Dense(64, activation='relu')(x)\n",
" x = Dropout(0.3)(x)\n",
" outputs = Dense(1, activation='sigmoid')(x)\n",
" \n",
" model = Model(inputs, outputs, name='cnn_classifier')\n",
" model.compile(\n",
" optimizer=Adam(learning_rate=1e-3),\n",
" loss='binary_crossentropy',\n",
" metrics=['accuracy', 'AUC']\n",
" )\n",
" return model\n",
" \n",
" @staticmethod\n",
" def create_lstm_classifier(input_dim: int) -> Model:\n",
" \"\"\"Bidirectional LSTM for sequence analysis.\"\"\"\n",
" inputs = Input(shape=(input_dim, 1))\n",
" \n",
" x = Bidirectional(LSTM(64, return_sequences=True))(inputs)\n",
" x = Dropout(0.3)(x)\n",
" x = Bidirectional(LSTM(32))(x)\n",
" x = Dropout(0.3)(x)\n",
" \n",
" x = Dense(32, activation='relu')(x)\n",
" outputs = Dense(1, activation='sigmoid')(x)\n",
" \n",
" model = Model(inputs, outputs, name='lstm_classifier')\n",
" model.compile(\n",
" optimizer=Adam(learning_rate=1e-3),\n",
" loss='binary_crossentropy',\n",
" metrics=['accuracy', 'AUC']\n",
" )\n",
" return model\n",
" \n",
" @staticmethod\n",
" def create_autoencoder(input_dim: int, encoding_dim: int = 32) -> tuple:\n",
" \"\"\"Autoencoder for anomaly detection.\"\"\"\n",
" # Encoder\n",
" inputs = Input(shape=(input_dim,))\n",
" x = Dense(128, activation='relu')(inputs)\n",
" x = BatchNormalization()(x)\n",
" x = Dense(64, activation='relu')(x)\n",
" x = BatchNormalization()(x)\n",
" encoded = Dense(encoding_dim, activation='relu', name='encoding')(x)\n",
" \n",
" # Decoder\n",
" x = Dense(64, activation='relu')(encoded)\n",
" x = BatchNormalization()(x)\n",
" x = Dense(128, activation='relu')(x)\n",
" x = BatchNormalization()(x)\n",
" decoded = Dense(input_dim, activation='linear')(x)\n",
" \n",
" autoencoder = Model(inputs, decoded, name='autoencoder')\n",
" autoencoder.compile(optimizer=Adam(1e-3), loss='mse')\n",
" \n",
" encoder = Model(inputs, encoded, name='encoder')\n",
" \n",
" return autoencoder, encoder\n",
" \n",
" @staticmethod\n",
" def create_multi_task_model(input_dim: int, num_tasks: int = 3) -> Model:\n",
" \"\"\"Multi-task model for multiple security domains.\"\"\"\n",
" inputs = Input(shape=(input_dim,))\n",
" \n",
" # Shared layers\n",
" shared = Dense(256, activation='relu')(inputs)\n",
" shared = BatchNormalization()(shared)\n",
" shared = Dropout(0.3)(shared)\n",
" shared = Dense(128, activation='relu')(shared)\n",
" shared = BatchNormalization()(shared)\n",
" shared = Dropout(0.2)(shared)\n",
" shared = Dense(64, activation='relu')(shared)\n",
" \n",
" # Task-specific heads\n",
" outputs = []\n",
" task_names = ['phishing', 'malware', 'intrusion']\n",
" for i in range(min(num_tasks, len(task_names))):\n",
" task_layer = Dense(32, activation='relu', name=f'{task_names[i]}_hidden')(shared)\n",
" task_output = Dense(1, activation='sigmoid', name=f'{task_names[i]}_output')(task_layer)\n",
" outputs.append(task_output)\n",
" \n",
" model = Model(inputs, outputs, name='multi_task_security')\n",
" model.compile(\n",
" optimizer=Adam(1e-3),\n",
" loss={f'{task_names[i]}_output': 'binary_crossentropy' for i in range(len(outputs))},\n",
" metrics=['accuracy']\n",
" )\n",
" return model\n",
"\n",
"print('✅ Deep learning architectures defined')"
]
},
{
"cell_type": "markdown",
"id": "abdaab25",
"metadata": {},
"source": [
"## 🎯 Training Pipeline"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "673c6e4b",
"metadata": {},
"outputs": [],
"source": [
"def prepare_data_for_training(df: pd.DataFrame, max_features: int = 50) -> tuple:\n",
" \"\"\"Prepare data for deep learning training.\"\"\"\n",
" \n",
" # Find target column\n",
" target_candidates = ['is_malicious', 'is_attack', 'is_malware', 'is_spam', \n",
" 'is_dga', 'is_miner', 'label', 'result']\n",
" target_col = None\n",
" for col in target_candidates:\n",
" if col in df.columns:\n",
" target_col = col\n",
" break\n",
" \n",
" if target_col is None:\n",
" # Find binary column\n",
" for col in df.columns:\n",
" if df[col].nunique() == 2 and col not in ['_category', '_dataset_id']:\n",
" target_col = col\n",
" break\n",
" \n",
" if target_col is None:\n",
" raise ValueError('No target column found')\n",
" \n",
" # Select numeric features\n",
" exclude = [target_col, '_category', '_dataset_id', 'source_dataset', 'url', 'payload', 'domain']\n",
" feature_cols = [c for c in df.select_dtypes(include=[np.number]).columns if c not in exclude]\n",
" \n",
" # Limit features\n",
" if len(feature_cols) > max_features:\n",
" feature_cols = feature_cols[:max_features]\n",
" \n",
" X = df[feature_cols].fillna(0).replace([np.inf, -np.inf], 0)\n",
" y = df[target_col].astype(int)\n",
" \n",
" # Scale\n",
" scaler = StandardScaler()\n",
" X_scaled = scaler.fit_transform(X)\n",
" \n",
" return X_scaled, y.values, feature_cols, scaler\n",
"\n",
"# Prepare data\n",
"X, y, features, scaler = prepare_data_for_training(combined_df)\n",
"print(f'📊 Data prepared: {X.shape}')\n",
"print(f' Features: {len(features)}')\n",
"print(f' Class balance: {np.bincount(y)}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9caabf5f",
"metadata": {},
"outputs": [],
"source": [
"# Split and balance data\n",
"X_train, X_test, y_train, y_test = train_test_split(\n",
" X, y, test_size=0.2, random_state=42, stratify=y\n",
")\n",
"\n",
"# Balance training data\n",
"try:\n",
" smote = SMOTE(random_state=42)\n",
" X_train_balanced, y_train_balanced = smote.fit_resample(X_train, y_train)\n",
" print(f'✅ After SMOTE: {len(X_train_balanced):,} training samples')\n",
"except:\n",
" X_train_balanced, y_train_balanced = X_train, y_train\n",
" print('⚠️ SMOTE skipped')\n",
"\n",
"print(f' Train: {len(X_train_balanced):,} | Test: {len(X_test):,}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ccee951f",
"metadata": {},
"outputs": [],
"source": [
"# Training callbacks\n",
"callbacks = [\n",
" EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True),\n",
" ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=5, min_lr=1e-6)\n",
"]\n",
"\n",
"# Train Transformer model\n",
"print('🔄 Training Transformer model...')\n",
"transformer = DeepSecurityModels.create_transformer_classifier(X.shape[1])\n",
"\n",
"history_transformer = transformer.fit(\n",
" X_train_balanced, y_train_balanced,\n",
" validation_split=0.2,\n",
" epochs=50,\n",
" batch_size=64,\n",
" callbacks=callbacks,\n",
" verbose=1\n",
")\n",
"\n",
"transformer_pred = (transformer.predict(X_test, verbose=0) > 0.5).astype(int).flatten()\n",
"transformer_auc = roc_auc_score(y_test, transformer.predict(X_test, verbose=0))\n",
"print(f'\\n✅ Transformer AUC: {transformer_auc:.4f}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5d0c55b2",
"metadata": {},
"outputs": [],
"source": [
"# Train CNN model\n",
"print('🔄 Training CNN model...')\n",
"\n",
"X_train_cnn = X_train_balanced.reshape(-1, X_train_balanced.shape[1], 1)\n",
"X_test_cnn = X_test.reshape(-1, X_test.shape[1], 1)\n",
"\n",
"cnn = DeepSecurityModels.create_cnn_classifier(X.shape[1])\n",
"\n",
"history_cnn = cnn.fit(\n",
" X_train_cnn, y_train_balanced,\n",
" validation_split=0.2,\n",
" epochs=50,\n",
" batch_size=64,\n",
" callbacks=callbacks,\n",
" verbose=1\n",
")\n",
"\n",
"cnn_pred = (cnn.predict(X_test_cnn, verbose=0) > 0.5).astype(int).flatten()\n",
"cnn_auc = roc_auc_score(y_test, cnn.predict(X_test_cnn, verbose=0))\n",
"print(f'\\n✅ CNN AUC: {cnn_auc:.4f}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3299c3c0",
"metadata": {},
"outputs": [],
"source": [
"# Train LSTM model\n",
"print('🔄 Training LSTM model...')\n",
"\n",
"lstm = DeepSecurityModels.create_lstm_classifier(X.shape[1])\n",
"\n",
"history_lstm = lstm.fit(\n",
" X_train_cnn, y_train_balanced, # Same shape as CNN\n",
" validation_split=0.2,\n",
" epochs=30, # LSTM is slower\n",
" batch_size=64,\n",
" callbacks=callbacks,\n",
" verbose=1\n",
")\n",
"\n",
"lstm_pred = (lstm.predict(X_test_cnn, verbose=0) > 0.5).astype(int).flatten()\n",
"lstm_auc = roc_auc_score(y_test, lstm.predict(X_test_cnn, verbose=0))\n",
"print(f'\\n✅ LSTM AUC: {lstm_auc:.4f}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c47177bf",
"metadata": {},
"outputs": [],
"source": [
"# Train Autoencoder for anomaly detection\n",
"print('🔄 Training Autoencoder...')\n",
"\n",
"# Train only on normal samples\n",
"X_normal = X_train_balanced[y_train_balanced == 0]\n",
"\n",
"autoencoder, encoder = DeepSecurityModels.create_autoencoder(X.shape[1])\n",
"\n",
"history_ae = autoencoder.fit(\n",
" X_normal, X_normal,\n",
" validation_split=0.2,\n",
" epochs=50,\n",
" batch_size=64,\n",
" callbacks=callbacks,\n",
" verbose=1\n",
")\n",
"\n",
"# Anomaly scores based on reconstruction error\n",
"reconstructions = autoencoder.predict(X_test, verbose=0)\n",
"mse = np.mean(np.power(X_test - reconstructions, 2), axis=1)\n",
"threshold = np.percentile(mse, 90) # Top 10% as anomalies\n",
"ae_pred = (mse > threshold).astype(int)\n",
"ae_auc = roc_auc_score(y_test, mse)\n",
"print(f'\\n✅ Autoencoder AUC: {ae_auc:.4f}')"
]
},
{
"cell_type": "markdown",
"id": "874d717c",
"metadata": {},
"source": [
"## 📊 Model Comparison"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "58a05f84",
"metadata": {},
"outputs": [],
"source": [
"# Compare all models\n",
"results = {\n",
" 'Transformer': {'pred': transformer_pred, 'auc': transformer_auc},\n",
" 'CNN': {'pred': cnn_pred, 'auc': cnn_auc},\n",
" 'LSTM': {'pred': lstm_pred, 'auc': lstm_auc},\n",
" 'Autoencoder': {'pred': ae_pred, 'auc': ae_auc}\n",
"}\n",
"\n",
"# Results table\n",
"print('📊 Deep Learning Model Comparison')\n",
"print('=' * 60)\n",
"print(f'{\"Model\":<15} {\"Accuracy\":<12} {\"F1\":<12} {\"AUC\":<12}')\n",
"print('-' * 60)\n",
"\n",
"for name, res in results.items():\n",
" acc = accuracy_score(y_test, res['pred'])\n",
" f1 = f1_score(y_test, res['pred'])\n",
" print(f'{name:<15} {acc:<12.4f} {f1:<12.4f} {res[\"auc\"]:<12.4f}')\n",
"\n",
"# Best model\n",
"best_model = max(results.items(), key=lambda x: x[1]['auc'])\n",
"print(f'\\n🏆 Best Model: {best_model[0]} (AUC: {best_model[1][\"auc\"]:.4f})')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6ffe5221",
"metadata": {},
"outputs": [],
"source": [
"# Visualize ROC curves\n",
"plt.figure(figsize=(10, 8))\n",
"\n",
"# Get probabilities\n",
"probs = {\n",
" 'Transformer': transformer.predict(X_test, verbose=0).flatten(),\n",
" 'CNN': cnn.predict(X_test_cnn, verbose=0).flatten(),\n",
" 'LSTM': lstm.predict(X_test_cnn, verbose=0).flatten(),\n",
" 'Autoencoder': mse / mse.max() # Normalized MSE\n",
"}\n",
"\n",
"colors = ['#4ecdc4', '#ff6b6b', '#ffe66d', '#95e1d3']\n",
"for (name, prob), color in zip(probs.items(), colors):\n",
" fpr, tpr, _ = roc_curve(y_test, prob)\n",
" auc = results[name]['auc']\n",
" plt.plot(fpr, tpr, label=f'{name} (AUC = {auc:.4f})', color=color, linewidth=2)\n",
"\n",
"plt.plot([0, 1], [0, 1], 'k--', alpha=0.5)\n",
"plt.xlabel('False Positive Rate', fontsize=12)\n",
"plt.ylabel('True Positive Rate', fontsize=12)\n",
"plt.title('🎯 Deep Learning ROC Comparison', fontsize=14)\n",
"plt.legend(loc='lower right')\n",
"plt.grid(True, alpha=0.3)\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ef891827",
"metadata": {},
"outputs": [],
"source": [
"# Training history visualization\n",
"fig, axes = plt.subplots(1, 3, figsize=(15, 4))\n",
"\n",
"histories = [\n",
" ('Transformer', history_transformer),\n",
" ('CNN', history_cnn),\n",
" ('LSTM', history_lstm)\n",
"]\n",
"\n",
"for ax, (name, hist) in zip(axes, histories):\n",
" ax.plot(hist.history['loss'], label='Train Loss')\n",
" ax.plot(hist.history['val_loss'], label='Val Loss')\n",
" ax.set_title(f'{name} Training', color='white')\n",
" ax.set_xlabel('Epoch')\n",
" ax.set_ylabel('Loss')\n",
" ax.legend()\n",
" ax.grid(True, alpha=0.3)\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"id": "7871e52a",
"metadata": {},
"source": [
"## 💾 Save Models"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0d7755e9",
"metadata": {},
"outputs": [],
"source": [
"# Save trained models\n",
"MODELS_DIR = Path.cwd().parent / 'models' / 'deep_learning'\n",
"MODELS_DIR.mkdir(parents=True, exist_ok=True)\n",
"\n",
"print('💾 Saving models...')\n",
"\n",
"# Save Keras models\n",
"transformer.save(MODELS_DIR / 'transformer_security.keras')\n",
"cnn.save(MODELS_DIR / 'cnn_security.keras')\n",
"lstm.save(MODELS_DIR / 'lstm_security.keras')\n",
"autoencoder.save(MODELS_DIR / 'autoencoder_security.keras')\n",
"encoder.save(MODELS_DIR / 'encoder_security.keras')\n",
"\n",
"# Save scaler and config\n",
"joblib.dump(scaler, MODELS_DIR / 'scaler.pkl')\n",
"joblib.dump(features, MODELS_DIR / 'feature_names.pkl')\n",
"\n",
"# Save metrics\n",
"metrics = {\n",
" name: {'accuracy': float(accuracy_score(y_test, r['pred'])),\n",
" 'f1': float(f1_score(y_test, r['pred'])),\n",
" 'auc': float(r['auc'])}\n",
" for name, r in results.items()\n",
"}\n",
"with open(MODELS_DIR / 'metrics.json', 'w') as f:\n",
" json.dump(metrics, f, indent=2)\n",
"\n",
"print(f'\\n✅ Models saved to {MODELS_DIR}')"
]
},
{
"cell_type": "markdown",
"id": "765404ff",
"metadata": {},
"source": [
"## 🎉 Summary\n",
"\n",
"### Trained Models:\n",
"- **Transformer** - Attention-based classifier\n",
"- **CNN** - Convolutional pattern detector\n",
"- **LSTM** - Sequence analyzer\n",
"- **Autoencoder** - Anomaly detector\n",
"\n",
"### Output Files:\n",
"```\n",
"models/deep_learning/\n",
"├── transformer_security.keras\n",
"├── cnn_security.keras\n",
"├── lstm_security.keras\n",
"├── autoencoder_security.keras\n",
"├── encoder_security.keras\n",
"├── scaler.pkl\n",
"├── feature_names.pkl\n",
"└── metrics.json\n",
"```\n",
"\n",
"These models are ready for integration with the Agentic AI security system!"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.15.0a3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|