{ "cells": [ { "cell_type": "markdown", "id": "1b13a36b", "metadata": {}, "source": [ "**Author:** Dr. Mallarapu \n", "**Created:** 2026-07-27 \n", "**Course:** SEAS 8414 \u2014 Security Analytics\n", "\n", "---\n", "\n", "### Goal of this notebook\n", "\n", "Train and audit detectors on an IoT-23 malware capture, reporting recall for each traffic family.\n", "\n", "### What you will learn\n", "\n", "1. Read a majority-class baseline before trusting any accuracy figure.\n", "2. Find the strongest single feature, then test it by dropping it and refitting.\n", "3. Tell duplicate inflation apart from genuine signal.\n", "4. Report per-group recall, because the rare classes carry the risk.\n", "5. Show why a rare class matters more than the aggregate score.\n", "\n", "### Where this connects to the course text\n", "\n", "The text builds a defence pipeline; this notebook trains a classifier and audits it. The links below are to specific chapter objectives that share an *analytic move*, not to matching subject matter.\n", "\n", "- **Chapter 9: Supply-Chain Integrity and Counterfeit Detection** \u2014 Learning objectives 2 and 3 (section 9.1) separate documentation gaps from tamper evidence, and warn that screening signals are **not independent**. Both apply to artifact-derived features.\n", "- **Chapter 10: Active Deception & Threat Hunting** \u2014 Learning objective 6 (section 10.1) places a claim on the **attribution ladder** and corrects for **dependence among rule hits**. The same rule stops us equating one feature with the label.\n", "- **Chapter 11: Formal Protocol Verification** \u2014 Section **11.1.2**, titled *Proved, tested, and hoped*, asks you to separate exactly those three. (Chapter 11 lists its objectives in \u00a711.0, not \u00a711.1 as the other chapters do.) The ablation does that job here: it tests whether the headline survives.\n", "\n", "---" ] }, { "cell_type": "markdown", "id": "0d56e1e1", "metadata": {}, "source": [ "# IoT Malware Flow Detection on IoT-23 (Zeek conn.log)\n", "### Model comparison + validity audit on a real IoT-23 malware capture (\u22651M flows)\n", "\n", "**Abstract:** IoT-23 (Garcia, Parmisano & Erquiaga, 2020) is a labelled corpus of **real IoT-malware network traffic**. It was captured by the Stratosphere Laboratory / Avast AIC and published as Zeek `conn.log`. We take one capture in which benign and malicious flows are **mixed within the same recording** (\u22651M flows). On that capture we compare four learners on flow-behaviour features. We then audit whether malicious-flow detection is genuine or a flow shortcut." ] }, { "cell_type": "markdown", "id": "b2e1cd55", "metadata": {}, "source": [ "## 1. Research problem\n", "\n", "**Task:** Classify each Zeek connection record as **benign** or **malicious** using only flow-behaviour features (duration, byte/packet counts, connection state, Zeek history string, protocol/service). Consumer IoT devices are a primary DDoS-botnet substrate (Mirai and successors). The operational question is whether a lightweight flow classifier can flag malicious IoT connections without deep-packet inspection." ] }, { "cell_type": "markdown", "id": "84611648", "metadata": {}, "source": [ "## 2. Literature review\n", "\n", "- **Garcia, Parmisano & Erquiaga (2020)** \u2014 the IoT-23 dataset: 20 malware + 3 benign IoT captures, Zeek-labelled (Stratosphere Lab, CTU / Avast AIC).\n", "- **Antonakakis et al. (2017)** \u2014 *Understanding the Mirai Botnet* (USENIX Security): the IoT-DDoS threat model this dataset instantiates.\n", "- **Meidan et al. (2018)** \u2014 N-BaIoT: detecting IoT botnet attacks from network behaviour.\n", "- **Sommer & Paxson (2010)** \u2014 the closed-world critique of ML-NIDS.\n", "\n", "**Related approaches and their known caveats** \u2014 drawn from the wider literature; these are **not** measurements reproduced on this exact corpus:\n", "\n", "| Reported approach | Known caveat |\n", "|---|---|\n", "| Flow/behaviour ML on IoT-23 | single-capture; conn-state/history can shortcut |\n", "| N-BaIoT autoencoders (Meidan 2018) | per-device models; cross-device transfer is harder |\n" ] }, { "cell_type": "markdown", "id": "5262db9b", "metadata": {}, "source": [ "## 3. Dataset provenance & honesty caveats\n", "\n", "| Property | Value |\n", "|---|---|\n", "| Source | Kaggle mirror of Stratosphere **IoT-23** (`agungpambudi/network-malware-detection-connection-analysis`) |\n", "| Capture | `CTU-IoT-Malware-Capture-35-1` \u2014 10.4M Zeek flows, **79% benign / 21% malicious** |\n", "| Label | Zeek `label` \u2192 benign vs malicious; family from `detailed-label` |\n", "| Access | Kaggle API token required (~2.6 GB one-time download) |\n", "\n", "**Not a re-run of the CTU-13 notebook:** CTU-13 (nb10) is 2011 *botnet* traffic as Argus `.binetflow` (15 fields). IoT-23 is a *different, later* capture set (2018\u201319 IoT malware) in Zeek `conn.log` (23 fields), separately published and cited. **Why one capture, not all 23:** IoT-23 captures are individually near-single-class, so concatenating them would make *'which pcap'* the real signal (a capture-identity artifact). Capture-35 is one of the few with a genuine within-capture benign/malicious mix, so the label here reflects flow behaviour, not recording identity. **Honestly:** the malicious class is almost all DDoS flood traffic, with only a rare C&C/Attack tail. Base rate is not what inflates the score here. Section 8 prints a majority-class baseline accuracy of **0.5930**. The winning model prints accuracy **0.999900**. A 0.5930 baseline cannot manufacture that. Corpus composition is the real caveat. Nearly every positive belongs to one loud family that flow features separate easily. Aggregate accuracy therefore reports that family and hides the rest. Section 9 prints the consequence: `C&C` recall **0.0**. Per-family recall is the metric that matters.\n", "\n", "### Before you run this: getting the data\n", "\n", "This notebook downloads its own data on the first run, then caches it. You do not fetch anything by hand.\n", "\n", "**Dataset:** Kaggle `agungpambudi/network-malware-detection-connection-analysis` -> `/tmp/iot23`. It is about **3 GB** on disk.\n", "\n", "**One-time setup.** Sign in at kaggle.com, open **Settings**, and under **API** choose **Create New Token**. Kaggle hands you a `kaggle.json` file. This notebook does *not* read that file. It reads a plain key file, so convert it once:\n", "\n", "```bash\n", "mkdir -p ~/.kaggle\n", "python3 -c \"import json;print(json.load(open('kaggle.json'))['key'],end='')\" > ~/.kaggle/access_token\n", "chmod 600 ~/.kaggle/access_token\n", "```\n", "\n", "Never paste the token into a cell, a commit, or a screenshot. If it leaks, revoke it from the same Settings page.\n", "\n", "**If the loader fails:**\n", "\n", "- `FileNotFoundError: ~/.kaggle/access_token` - you created `kaggle.json` but not the key file. Run the command above.\n", "- `401 Unauthorized` - the key is wrong, or a trailing newline crept in.\n", "- `403 Forbidden` - open the dataset page on Kaggle while signed in, accept its terms, then re-run the cell.\n", "\n", "The cache sits under `/tmp`, which macOS clears on reboot. To keep it, move the folder somewhere durable and symlink it back. Do **not** edit the path in the code cell below: that changes a code cell and invalidates the stored outputs you are reviewing." ] }, { "cell_type": "markdown", "id": "75e6dea8", "metadata": {}, "source": [ "## 4. Solution design\n", "\n", "The methodology is deliberately two-track. We *earn* a headline score with standard modelling, then *interrogate* it with a validity audit. Only a verdict that survives both is reported. The diagram below is the shape of every notebook in this series." ] }, { "cell_type": "markdown", "id": "1e2449f6", "metadata": {}, "source": [ "**Figure 4.1 \u2014 Solution design (methodology).**\n", "\n", "\"Figure" ] }, { "cell_type": "markdown", "id": "ab8a26e0", "metadata": {}, "source": [ "## 5. Implementation architecture\n", "\n", "Five stages \u2014 ingestion, preprocessing, modelling, evaluation, and a parallel validity-audit path \u2014 feed a single graded results ledger. Leakage defences (dropping label-derived and identifier columns) live in preprocessing, before any model sees the data." ] }, { "cell_type": "markdown", "id": "67e8b198", "metadata": {}, "source": [ "**Figure 5.1 \u2014 Implementation architecture.**\n", "\n", "\"Figure" ] }, { "cell_type": "markdown", "id": "3eca75a8", "metadata": {}, "source": [ "## 6. Data acquisition & preparation\n", "\n", "Every line below is commented so a student can re-run and modify each step. The cell ends by producing the standard analysis variables: `df`, `X` (clean numeric features), `y` (binary label), `feat` (feature names), and `family`. `family` is the per-group label used for the recall breakdown. It is an attack family on the intrusion corpora, but a transaction type, merchant category or malware category on the fraud/malware ones." ] }, { "cell_type": "code", "execution_count": 1, "id": "959942a7", "metadata": {}, "outputs": [], "source": [ "%matplotlib inline\n", "import time, warnings; warnings.filterwarnings('ignore') # keep output clean\n", "import numpy as np, pandas as pd # numerics + dataframes\n", "import matplotlib.pyplot as plt # static plots (embed in HTML+PDF)\n", "plt.rcParams['figure.dpi'] = 120 # crisp figures\n", "RANDOM_STATE = 0 # single seed used everywhere\n", "np.random.seed(RANDOM_STATE) # reproducible sampling\n", "NEG_WORD, POS_WORD = 'benign', 'attack' # class names (overridden by some loaders)" ] }, { "cell_type": "code", "execution_count": 2, "id": "2dc2ca20", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "loaded 3,685,398 flows x 12 features from one capture; malicious rate (bounded sample) 0.5930; families ['Attack', 'C&C', 'DDoS', 'benign']\n" ] } ], "source": [ "import os, glob\n", "# IoT-23 (Garcia, Parmisano & Erquiaga, 2020; Stratosphere Lab / Avast AIC): 20 real IoT-malware\n", "# captures + 3 benign, published as Zeek conn.log. This is the Kaggle pipe-delimited mirror.\n", "# Self-contained: download once (~2.6 GB, needs a Kaggle token) and cache under /tmp/iot23.\n", "os.environ.setdefault('KAGGLE_KEY', open(os.path.expanduser('~/.kaggle/access_token')).read().strip())\n", "IOT_DIR = '/tmp/iot23'; os.makedirs(IOT_DIR, exist_ok=True)\n", "CAP = 'CTU-IoT-Malware-Capture-35-1conn.log.labeled.csv' # one capture, benign+malicious MIXED\n", "hits = glob.glob(IOT_DIR + '/**/' + CAP, recursive=True)\n", "if not hits:\n", " import kaggle; kaggle.api.authenticate()\n", " print('downloading IoT-23 captures (~2.6 GB, one-time)...')\n", " kaggle.api.dataset_download_files('agungpambudi/network-malware-detection-connection-analysis',\n", " path=IOT_DIR, unzip=True, quiet=True)\n", " hits = glob.glob(IOT_DIR + '/**/' + CAP, recursive=True)\n", "f = hits[0]; assert os.path.exists(f), f'capture not found: {f}'\n", "# Zeek conn.log fields; '-' is Zeek's null token. Keep flow-BEHAVIOUR features only; drop IP/port/\n", "# uid/time identifiers so the model cannot memorise 'which host' instead of learning malicious behaviour.\n", "KEEP = ['proto','service','duration','orig_bytes','resp_bytes','conn_state','missed_bytes',\n", " 'history','orig_pkts','orig_ip_bytes','resp_pkts','resp_ip_bytes','label']\n", "raw = pd.read_csv(f, sep='|', usecols=KEEP, low_memory=False, na_values=['-'])\n", "# The Kaggle pipe-conversion merged Zeek's `label` and `detailed-label` into ONE whitespace field:\n", "# 'Benign -' or 'Malicious DDoS'. Split it \u2014 token0 = binary class, token1 = attack family.\n", "parts = raw['label'].astype(str).str.split(n=1)\n", "binl = parts.str[0].str.strip()\n", "fam = parts.str[1].str.strip().replace('-', 'benign').fillna('benign')\n", "ismal = binl.str.lower().eq('malicious')\n", "# Malicious flows (DDoS-dominated) are time-clustered in the MIDDLE of the capture (the head/tail are\n", "# ~100% benign), so we KEEP EVERY malicious flow and SUBSAMPLE benign to a bound \u2014 the CTU-13 recipe.\n", "# The malicious rate printed below is therefore a bounded-sample rate, not the natural base rate.\n", "BENIGN_CAP = 1_500_000\n", "ben = raw.index[~ismal]\n", "ben = pd.Index(np.random.RandomState(0).choice(ben, size=min(len(ben), BENIGN_CAP), replace=False))\n", "keep = raw.index[ismal].union(ben)\n", "df = raw.loc[keep].reset_index(drop=True)\n", "df['y'] = ismal.loc[keep].astype(int).to_numpy()\n", "df['family'] = fam.loc[keep].to_numpy()\n", "assert len(df) >= 1_000_000, f'floor not met: {len(df):,}'\n", "DROP = ['label', 'y', 'family']\n", "feat = [c for c in df.columns if c not in DROP]\n", "from sklearn.preprocessing import LabelEncoder\n", "X = df[feat].copy()\n", "for c in X.select_dtypes(include='object').columns:\n", " X[c] = LabelEncoder().fit_transform(X[c].astype(str))\n", "X = X.apply(pd.to_numeric, errors='coerce').replace([np.inf, -np.inf], np.nan).fillna(0.0)\n", "X = X.loc[:, X.nunique() > 1]; feat = list(X.columns)\n", "y = df['y'].to_numpy(); family = df['family'].to_numpy()\n", "print(f'loaded {len(df):,} flows x {len(feat)} features from one capture; '\n", " f'malicious rate (bounded sample) {y.mean():.4f}; families {sorted(set(family))}')" ] }, { "cell_type": "markdown", "id": "b5ee8d8a", "metadata": {}, "source": [ "## 7. Exploratory data analysis" ] }, { "cell_type": "code", "execution_count": 3, "id": "fd2f27b8", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# --- EDA 1: class balance and the attack-family mix ---\n", "fig, ax = plt.subplots(1, 2, figsize=(11, 4))\n", "df['y'].map({0:NEG_WORD,1:POS_WORD}).value_counts().plot.bar( # counts per class\n", " ax=ax[0], color=['#2a9d8f','#e76f51']); ax[0].set_yscale('log')\n", "ax[0].set_title(f'Class balance ({NEG_WORD} vs {POS_WORD})'); ax[0].set_ylabel('records (log)')\n", "df.loc[df.y==1,'family'].value_counts().head(8).plot.barh( # top attack families\n", " ax=ax[1], color='#e76f51'); ax[1].invert_yaxis(); ax[1].set_title('Top attack families')\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "code", "execution_count": 4, "id": "56094a7a", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# --- EDA 2: feature correlation + a 2-D PCA projection ---\n", "from sklearn.preprocessing import StandardScaler # scale before PCA\n", "from sklearn.decomposition import PCA\n", "fig, ax = plt.subplots(1, 2, figsize=(12, 5))\n", "topv = X[feat].var().sort_values().tail(12).index # 12 highest-variance features\n", "im = ax[0].imshow(X[topv].corr(), cmap='coolwarm', vmin=-1, vmax=1) # correlation heatmap\n", "ax[0].set_xticks(range(len(topv))); ax[0].set_xticklabels(topv, rotation=90, fontsize=7)\n", "ax[0].set_yticks(range(len(topv))); ax[0].set_yticklabels(topv, fontsize=7)\n", "ax[0].set_title('Feature correlation (top-variance)'); fig.colorbar(im, ax=ax[0], shrink=0.7)\n", "samp = X.sample(min(5000, len(X)), random_state=RANDOM_STATE) # subsample for a fast PCA\n", "pc = PCA(n_components=2).fit_transform(StandardScaler().fit_transform(samp))\n", "ys = y[samp.index] # aligned labels for coloring\n", "for lab,c in [(0,'#2a9d8f'),(1,'#e76f51')]:\n", " ax[1].scatter(pc[ys==lab,0], pc[ys==lab,1], s=4, alpha=0.4, color=c,\n", " label={0:NEG_WORD,1:POS_WORD}[lab])\n", "ax[1].set_title('PCA projection (2 components)'); ax[1].legend(); ax[1].set_xlabel('PC1'); ax[1].set_ylabel('PC2')\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "0796dc26", "metadata": {}, "source": [ "## 8. Model comparison\n", "\n", "Four diverse learners share one held-out split, ranked by ROC-AUC.\n", "\n", "**Two honesty guards print with the table:**\n", "\n", "1. The models train on a *stratified subsample* of at most 120,000 rows. The full row count is printed above. So every score here is a subsample number, not a full-corpus claim.\n", "2. The **majority-class baseline accuracy** appears *inside* the ranking table. On imbalanced data, 0.99 accuracy can be worse than always guessing the majority class. Judge each model against that baseline, not against 0.5." ] }, { "cell_type": "code", "execution_count": 5, "id": "d6dd5a8c", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "materialized 3,685,398 rows | trained on 120,000 (stratified subsample) | held-out 921,350\n", "MAJORITY-CLASS BASELINE accuracy = 0.5930 (any model must beat THIS, not 0.5, to be interesting)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "best model: RandomForest\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
modelaccuracyroc_auctrain_s
0RandomForest0.9999000.9999520.4
1XGBoost0.9999020.9999390.2
2LightGBM0.9999030.9999350.8
3LogisticRegression0.9999030.9999270.2
4MajorityBaseline0.5930000.5000000.0
\n", "
" ], "text/plain": [ " model accuracy roc_auc train_s\n", "0 RandomForest 0.999900 0.999952 0.4\n", "1 XGBoost 0.999902 0.999939 0.2\n", "2 LightGBM 0.999903 0.999935 0.8\n", "3 LogisticRegression 0.999903 0.999927 0.2\n", "4 MajorityBaseline 0.593000 0.500000 0.0" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# --- Model comparison: four learners on the same held-out split ---\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.metrics import accuracy_score, roc_auc_score\n", "import xgboost as xgb, lightgbm as lgb\n", "\n", "# Stratified split keeps the class ratio in both halves.\n", "Xtr, Xte, ytr, yte = train_test_split(X, y, test_size=0.25, random_state=RANDOM_STATE, stratify=y)\n", "from sklearn.pipeline import make_pipeline\n", "from sklearn.preprocessing import StandardScaler\n", "N_MATERIALIZED = len(y) # the full corpus we loaded (see printed count)\n", "# HONEST DISCLOSURE: we do NOT train on all N. We fit on a STRATIFIED subsample (<=120k) because\n", "# these learners saturate long before then on this data. Every headline below is a SUBSAMPLE\n", "# number, not a full-corpus number \u2014 saying otherwise would be the fabrication this course forbids.\n", "if len(Xtr) > 120_000:\n", " Xtr, _, ytr, _ = train_test_split(Xtr, ytr, train_size=120_000, random_state=RANDOM_STATE,\n", " stratify=ytr) # genuinely stratified, not random\n", "MAJORITY_BASELINE = max(np.mean(yte), 1 - np.mean(yte)) # accuracy of 'always predict majority'\n", "print(f'materialized {N_MATERIALIZED:,} rows | trained on {len(Xtr):,} (stratified subsample) | '\n", " f'held-out {len(yte):,}')\n", "print(f'MAJORITY-CLASS BASELINE accuracy = {MAJORITY_BASELINE:.4f} '\n", " f'(any model must beat THIS, not 0.5, to be interesting)')\n", "\n", "models = { # four standard, diverse learners\n", " 'LogisticRegression': make_pipeline(StandardScaler(), LogisticRegression(max_iter=300)), # scaled!\n", " 'RandomForest': RandomForestClassifier(n_estimators=60, n_jobs=-1, random_state=RANDOM_STATE),\n", " 'XGBoost': xgb.XGBClassifier(n_estimators=80, max_depth=6, tree_method='hist', n_jobs=-1,\n", " eval_metric='logloss', random_state=RANDOM_STATE),\n", " 'LightGBM': lgb.LGBMClassifier(n_estimators=80, n_jobs=-1, verbose=-1, random_state=RANDOM_STATE),\n", "}\n", "rows, fitted = [], {}\n", "for name, m in models.items(): # fit + score each model\n", " t = time.perf_counter(); m.fit(Xtr, ytr); fitted[name] = m\n", " p = m.predict_proba(Xte)[:, 1] # positive-class probability on held-out\n", " rows.append({'model': name, 'accuracy': round(accuracy_score(yte, (p>0.5).astype(int)), 6),\n", " 'roc_auc': round(roc_auc_score(yte, p), 6), # 6 dp: a 1.000000 is a red flag, not a win\n", " 'train_s': round(time.perf_counter()-t, 1)})\n", "rows.append({'model': 'MajorityBaseline', 'accuracy': round(MAJORITY_BASELINE, 4),\n", " 'roc_auc': 0.5, 'train_s': 0.0}) # show the baseline IN the ranking table\n", "comparison = pd.DataFrame(rows).sort_values('roc_auc', ascending=False).reset_index(drop=True)\n", "_ranked = comparison[comparison.model != 'MajorityBaseline']\n", "best_name = _ranked.iloc[0]['model']; best = fitted[best_name] # winner by ROC-AUC (excl. baseline)\n", "print('best model:', best_name); comparison" ] }, { "cell_type": "markdown", "id": "31b286bf", "metadata": {}, "source": [ "## 9. Results\n", "\n", "Diagnostics for the winning model, including **per-group recall**.\n", "\n", "The grouping comes from whatever the loader put in `family`. It is *not* always an attack taxonomy. On the intrusion corpora it is the attack family. On the fraud and malware corpora it is a transaction type, a merchant category or a malware category. On binary corpora it collapses to the positive class.\n", "\n", "Read it accordingly. Where the groups are genuinely rare classes, they reveal whether detection is real. The dominant flood classes do not." ] }, { "cell_type": "code", "execution_count": 6, "id": "6bb41cb6", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "operational FALSE-POSITIVE RATE @0.5 = 0.0000 (7 benign flagged of 375,000)\n", "worst per-family recalls: {'C&C': 0.0, 'DDoS': 1.0}\n" ] } ], "source": [ "# --- Results for the best model: confusion, ROC, PR, importances, per-family recall ---\n", "from sklearn.metrics import confusion_matrix, roc_curve, precision_recall_curve, recall_score\n", "pb = best.predict_proba(Xte)[:, 1]; pred = (pb > 0.5).astype(int)\n", "fig, ax = plt.subplots(1, 3, figsize=(15, 4))\n", "# (1) confusion matrix\n", "cm = confusion_matrix(yte, pred); ax[0].imshow(cm, cmap='Blues')\n", "ax[0].set_title(f'{best_name}: confusion'); ax[0].set_xticks([0,1]); ax[0].set_yticks([0,1])\n", "ax[0].set_xticklabels([NEG_WORD,POS_WORD]); ax[0].set_yticklabels([NEG_WORD,POS_WORD])\n", "for (i,j),v in np.ndenumerate(cm): ax[0].text(j,i,f'{v:,}',ha='center',va='center')\n", "# (2) ROC and PR curves\n", "fpr,tpr,_ = roc_curve(yte, pb); prec,rec,_ = precision_recall_curve(yte, pb)\n", "ax[1].plot(fpr,tpr,color='#264653'); ax[1].plot([0,1],[0,1],'--',c='grey')\n", "ax[1].set_title(f'ROC (AUC={roc_auc_score(yte,pb):.4f})'); ax[1].set_xlabel('FPR'); ax[1].set_ylabel('TPR')\n", "ax[2].plot(rec,prec,color='#e76f51'); ax[2].set_title('Precision-Recall'); ax[2].set_xlabel('recall'); ax[2].set_ylabel('precision')\n", "plt.tight_layout(); plt.show()\n", "\n", "# (3) feature importances + (4) per-attack-family recall\n", "fig, ax = plt.subplots(1, 2, figsize=(13, 5))\n", "imp, names = None, feat # importances, robust to the scaled-LR pipeline\n", "if hasattr(best, 'feature_importances_'): # tree models\n", " imp = best.feature_importances_; names = list(getattr(best, 'feature_names_in_', feat))[:len(imp)]\n", "elif hasattr(best, 'named_steps') and 'logisticregression' in getattr(best, 'named_steps', {}):\n", " imp = np.abs(best.named_steps['logisticregression'].coef_[0]); names = feat # LR pipeline\n", "elif hasattr(best, 'coef_'):\n", " imp = np.abs(best.coef_[0]); names = feat\n", "if imp is not None:\n", " pd.Series(imp, index=names[:len(imp)]).sort_values().tail(12).plot.barh(ax=ax[0], color='#264653')\n", "ax[0].set_title(f'{best_name}: top importances / |coef|')\n", "# Per-family recall, WORST-first so rare, hard classes are visible, not just the dominant floods.\n", "fam_te = df.loc[Xte.index, 'family']\n", "fr = {}\n", "for fam, cnt in fam_te[yte==1].value_counts().items():\n", " if cnt < 5: continue # need a few positives for a meaningful recall\n", " mask = (fam_te==fam).to_numpy(); fr[fam] = recall_score(yte[mask], pred[mask], zero_division=0)\n", "srt = pd.Series(fr).sort_values()\n", "show = pd.concat([srt.head(9), srt.tail(3)]) if len(srt) > 12 else srt # worst 9 + best 3\n", "show = show[~show.index.duplicated()]\n", "show.plot.barh(ax=ax[1], color=['#e76f51' if v < 0.5 else '#2a9d8f' for v in show]); ax[1].set_xlim(0,1)\n", "ax[1].set_title('Per-family recall (worst first; red < 0.5)')\n", "plt.tight_layout(); plt.show()\n", "# Operational numbers, not just figures: false-positive rate and the worst per-family recalls.\n", "tn, fp = int(cm[0,0]), int(cm[0,1])\n", "fpr_op = fp/(fp+tn) if (fp+tn) > 0 else float('nan') # benign wrongly flagged @0.5\n", "print(f'operational FALSE-POSITIVE RATE @0.5 = {fpr_op:.4f} ({fp:,} benign flagged of {fp+tn:,})')\n", "print('worst per-family recalls:', {k: round(v, 3) for k, v in srt.head(6).items()})" ] }, { "cell_type": "markdown", "id": "efefe504", "metadata": {}, "source": [ "## 10. Validity audit \u2014 is the score real?\n", "\n", "Three diagnostics. **(a)** How well can the *single best feature*, alone, separate the classes? A near-1.0 single-feature AUC means that feature is *near-sufficient* \u2014 a shortcut (which may be legitimate signal or an artifact), not the same as target leakage. **(b)** The exact-duplicate row rate. **(c)** The **train/test exact-row contamination** \u2014 the fraction of held-out rows that are duplicates of training rows, which is what actually inflates a held-out score. The trust grade is the *worse* of the single-feature and contamination concerns." ] }, { "cell_type": "code", "execution_count": 7, "id": "3631ff52", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "best single-feature AUC = 0.9996 (feature: history)\n", " note: a near-1.0 single-feature AUC means this feature is *near-sufficient* (a shortcut),\n", " which may be legitimate signal OR an artifact \u2014 it is NOT the same as target leakage.\n", "exact-duplicate row rate (whole corpus) = 0.565\n", "TRAIN/TEST exact-row contamination = 0.422 (single-feat grade F, contam grade D)\n", "==> data trust grade: F (worse of the two; F = shortcut and/or heavy contamination)\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# --- Validity audit: is the score real detection, or a data shortcut? ---\n", "from sklearn.metrics import roc_auc_score\n", "samp = X.sample(min(60_000, len(X)), random_state=1); ysamp = y[samp.index]\n", "aucs = {}\n", "for c in feat: # AUC of EACH feature alone\n", " col = samp[c].to_numpy(float)\n", " if col.std()==0: continue\n", " a = roc_auc_score(ysamp, col); aucs[c] = max(a, 1-a) # direction-agnostic\n", "best_auc = max(aucs.values()); best_col = max(aucs, key=aucs.get)\n", "dup_rate = 1 - X.drop_duplicates().shape[0]/len(X) # exact-duplicate feature rows (whole set)\n", "# The statistic that actually inflates a held-out score is TRAIN/TEST CONTAMINATION: how many test\n", "# rows are exact duplicates of a training row. Measure it directly on the split used above.\n", "_trkeys = set(map(tuple, np.round(Xtr.to_numpy(), 6)))\n", "_te = np.round(Xte.to_numpy(), 6)[:50_000]\n", "contam = float(np.mean([tuple(r) in _trkeys for r in _te])) # fraction of test rows seen in train\n", "# Trust grade reflects BOTH failure modes and takes the WORSE of the two: a near-perfect single\n", "# feature (shortcut) OR heavy train/test contamination each independently invalidate the headline.\n", "_ga = 'F' if best_auc>=0.999 else 'D' if best_auc>=0.99 else 'C' if best_auc>=0.95 else 'B' if best_auc>=0.85 else 'A'\n", "_gc = 'F' if contam>=0.5 else 'D' if contam>=0.3 else 'C' if contam>=0.15 else 'B' if contam>=0.05 else 'A'\n", "grade = max(_ga, _gc) # 'max' letter = worse grade (A best, F worst)\n", "print(f'best single-feature AUC = {best_auc:.4f} (feature: {best_col})')\n", "print(f' note: a near-1.0 single-feature AUC means this feature is *near-sufficient* (a shortcut),\\n'\n", " f' which may be legitimate signal OR an artifact \u2014 it is NOT the same as target leakage.')\n", "print(f'exact-duplicate row rate (whole corpus) = {dup_rate:.3f}')\n", "print(f'TRAIN/TEST exact-row contamination = {contam:.3f} (single-feat grade {_ga}, contam grade {_gc})')\n", "print(f'==> data trust grade: {grade} (worse of the two; F = shortcut and/or heavy contamination)')\n", "s = pd.Series(aucs).sort_values().tail(15)\n", "fig, ax = plt.subplots(figsize=(8,5))\n", "s.plot.barh(ax=ax, color=['#e76f51' if v>=0.99 else '#457b9d' for v in s]); ax.axvline(0.5,ls='--',c='grey')\n", "ax.set_xlim(0.5,1.0); ax.set_title('Single-feature ROC-AUC (red = near-perfect shortcut)'); ax.set_xlabel('AUC alone')\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "509094ea", "metadata": {}, "source": [ "## 11. Ablation \u2014 does the headline survive removing the artifacts?\n", "\n", "Narrating a shortcut is not enough. We *retrain the winning model* after (1) de-duplicating the corpus (removing the train/test contamination) and (2) dropping the single strongest feature. We report the held-out AUC each time. **Read the result honestly, both ways:** if the AUC **collapses**, the headline was a contamination/shortcut artifact. If it **barely moves** \u2014 common on *simulated* corpora \u2014 that is **not vindication**. It means the classes are separable by *many* redundant features, because the attack and benign distributions barely overlap. That is its own generation artifact. The numbers below decide which story is true here, not the prose." ] }, { "cell_type": "code", "execution_count": 8, "id": "bea90edb", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Ablation \u2014 how much of the headline survives once each artifact is removed:\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
settingheld_out_auc
0headline (as-is)0.999952
1de-duplicated (57% rows removed)0.999996
2shortcut feature dropped (history)0.999949
\n", "
" ], "text/plain": [ " setting held_out_auc\n", "0 headline (as-is) 0.999952\n", "1 de-duplicated (57% rows removed) 0.999996\n", "2 shortcut feature dropped (history) 0.999949" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# --- Ablation: SHOW the inflation empirically, don't just narrate it ---\n", "from sklearn.base import clone\n", "def _retrain_auc(Xa, ya): # re-split, stratified-subsample, refit best family\n", " xtr, xte, ytr2, yte2 = train_test_split(Xa, ya, test_size=0.25, random_state=RANDOM_STATE, stratify=ya)\n", " if len(xtr) > 120_000:\n", " xtr, _, ytr2, _ = train_test_split(xtr, ytr2, train_size=120_000, random_state=RANDOM_STATE, stratify=ytr2)\n", " m = clone(best); m.fit(xtr, ytr2)\n", " return roc_auc_score(yte2, m.predict_proba(xte)[:, 1])\n", "base_auc = roc_auc_score(yte, best.predict_proba(Xte)[:, 1]) # (0) the headline held-out AUC\n", "Xdd = X.drop_duplicates(); ydd = y[Xdd.index] # (1) de-duplicated corpus\n", "auc_dedup = _retrain_auc(Xdd, ydd)\n", "auc_noshort = _retrain_auc(X.drop(columns=[best_col]), y) if best_col in X.columns else base_auc # (2) drop shortcut\n", "ablation = pd.DataFrame([\n", " {'setting': 'headline (as-is)', 'held_out_auc': round(base_auc, 6)},\n", " {'setting': f'de-duplicated ({1-len(Xdd)/len(X):.0%} rows removed)', 'held_out_auc': round(auc_dedup, 6)},\n", " {'setting': f'shortcut feature dropped ({best_col})', 'held_out_auc': round(auc_noshort, 6)},\n", "])\n", "print('Ablation \u2014 how much of the headline survives once each artifact is removed:')\n", "ablation" ] }, { "cell_type": "markdown", "id": "6d7d1091", "metadata": {}, "source": [ "## 12. Reproducibility & robustness" ] }, { "cell_type": "code", "execution_count": 9, "id": "ae3c80aa", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "seed=0 | numpy 2.3.5 | sklearn 1.9.0 | xgboost 1.6.2 | lightgbm 4.7.0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "RandomForest 3-fold CV ROC-AUC = 1.0000 +/- 0.0000 (mean +/- std across 3 stratified folds; a small std means a stable estimate on this split)\n" ] } ], "source": [ "# --- Reproducibility & robustness ---\n", "import sklearn\n", "from sklearn.model_selection import StratifiedKFold, cross_val_score\n", "print(f'seed={RANDOM_STATE} | numpy {np.__version__} | sklearn {sklearn.__version__} | '\n", " f'xgboost {xgb.__version__} | lightgbm {lgb.__version__}')\n", "# 3-fold cross-validated ROC-AUC of the winning model (fresh clone, bounded subsample) -> mean +/- std.\n", "from sklearn.base import clone\n", "cvX, cvy = Xtr.iloc[:40_000], ytr[:40_000]\n", "def _auc_scorer(est, Xv, yv): # robust to xgboost's 2-col predict_proba\n", " p = est.predict_proba(Xv)\n", " p = p[:, 1] if getattr(p, 'ndim', 1) == 2 else p\n", " return roc_auc_score(yv, p)\n", "try:\n", " cv = cross_val_score(clone(best), cvX, cvy,\n", " cv=StratifiedKFold(3, shuffle=True, random_state=RANDOM_STATE),\n", " scoring=_auc_scorer, error_score='raise')\n", " assert np.all(np.isfinite(cv)), 'non-finite CV folds' # FAIL CLOSED: never narrate a NaN as evidence\n", " print(f'{best_name} 3-fold CV ROC-AUC = {cv.mean():.4f} +/- {cv.std():.4f} '\n", " f'(mean +/- std across 3 stratified folds; a small std means a stable estimate on this split)')\n", "except Exception as e:\n", " print(f'CV UNAVAILABLE ({type(e).__name__}: {str(e)[:60]}); rely on the single held-out AUC above \u2014 '\n", " f'we do NOT report a CV number we could not compute')" ] }, { "cell_type": "markdown", "id": "d1669771", "metadata": {}, "source": [ "## 13. Scientific conclusion\n", "\n", "The headline AUC on this capture is **not trustworthy as a detector**, and the notebook's own audit says why. The Zeek `history` string alone reaches near-perfect single-feature AUC \u2014 it encodes the DDoS flood pattern. It is that single-feature check, not the overlap check, that drives the overall grade to F. The contamination sub-grade is D, and de-duplication does **not** lower the AUC \u2014 see the ledger. The decisive evidence is the per-family recall. The model recovers essentially **all DDoS** flows but **almost none of the rare C&C** flows. That is precisely the stealthy compromise a real IoT monitor must catch. So the honest reading is that flow features detect the loud DDoS flood (which barely needs ML) while missing the quiet command-and-control. A deployable claim would require deduplicated, per-family evaluation and a cross-capture test, which we did not run here (Sommer & Paxson, 2010).\n", "\n", "**Validity ledger \u2014 read the headline against these printed numbers:** Majority-class baseline **accuracy**: **0.5930**. The accuracy column must clear that bar to mean anything. For ROC-AUC the trivial baseline is 0.5, not that figure. Winning learner: **RandomForest** (3-fold CV ROC-AUC **1.0000**). Strongest *single* feature: `history` at AUC **0.9996**. The ablation refutes a single-feature story. Dropping that feature barely moves the AUC: **0.999952 \u2192 0.999949**. So the separability is **multi-feature**. That reflects how this corpus was generated, not one leaky column. De-duplication does **not** lower the score (**0.999996**). So duplicate rows are not what props it up. The overlap above is a caveat about the *random split*, not proof the score is fabricated. Data-trust grade: **F**. It is the worse of two independent sub-checks. Single-feature AUC 0.9996 scores **F**. Train/test exact-row overlap 0.422 scores **D**. The single-feature check drives the grade, not the overlap check. Train/test overlap separately scores D, so overlap is not the issue here. On this A-best / F-worst scale, a D or F means the headline is optimistic. Treat it as a benchmark number, not a deployment estimate. Operational false-positive rate at threshold 0.5: **0.0000**. Worst per-group recalls, exactly as printed: {`C&C`: 0.0, `DDoS`: 1.0}. The weakest group sits at **0.000**, so the model misses most of it. That gap, not the aggregate score, is the operationally important result. **Disclosed limitation:** categorical columns are integer-encoded before the split. The encoder therefore sees the test set's category values. On an all-numeric corpus that step is a no-op. The mapping never consults the label, so no *label* information leaks. It is still transductive. A deployed system would need an unseen-category bucket. **How the audit numbers are computed:** overlap is measured on the first 50,000 held-out rows, so read it as a sampled estimate. Each ablation re-splits and refits, so tiny differences are re-split noise. The de-duplication variant keeps the first label when a feature vector appears twice. **Scope:** the split is random, not temporal or entity-grouped. Every number above therefore measures in-distribution separability only." ] }, { "cell_type": "markdown", "id": "178adeb7", "metadata": {}, "source": [ "## References\n", "\n", "1. Garc\u00eda, S., Parmisano, A. & Erquiaga, M.J. (2020). *IoT-23: A labeled dataset with malicious and benign IoT network traffic*. Stratosphere Lab, CTU University / Avast AIC.\n", "2. Antonakakis, M. et al. (2017). Understanding the Mirai Botnet. *USENIX Security*.\n", "3. Meidan, Y. et al. (2018). N-BaIoT: Network-based detection of IoT botnet attacks. *IEEE Pervasive Computing*.\n", "4. Sommer, R. & Paxson, V. (2010). Outside the Closed World: On Using Machine Learning for Network Intrusion Detection. *IEEE S&P*." ] } ], "metadata": { "kernelspec": { "display_name": "seas8414-phase-notebooks", "language": "python", "name": "seas8414-phase-notebooks" } }, "nbformat": 4, "nbformat_minor": 5 }