init commit

lab5/train_sqli_model.py

@@ -0,0 +1,77 @@
+import joblib
+import csv
+import sys
+from pathlib import Path
+
+import numpy as np
+from scipy.sparse import hstack
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+from sklearn.model_selection import train_test_split
+
+sys.path.append(str(Path(__file__).resolve().parent.parent))
+from common.features import handcrafted_feature_matrix  # noqa: E402
+
+SQL_KEYWORDS = [
+    "select", "union", "drop", "insert", "update", "delete", "or 1=1",
+    "sleep(", "xp_cmdshell", "--", "exec ", "'or'", "1=1",
+]
+
+
+def load_data(path="data.csv"):
+    texts, labels = [], []
+    with open(path, newline="", encoding="utf-8") as f:
+        for row in csv.DictReader(f):
+            texts.append(row["text"])
+            labels.append(int(row["label"]))
+    return texts, np.array(labels)
+
+
+def main():
+    texts, labels = load_data()
+    X_train_txt, X_test_txt, y_train, y_test = train_test_split(
+        texts, labels, test_size=0.25, random_state=42, stratify=labels
+    )
+
+    vectorizer = TfidfVectorizer(analyzer="char_wb", ngram_range=(2, 4), max_features=1500)
+    Xtr_tfidf = vectorizer.fit_transform(X_train_txt)
+    Xte_tfidf = vectorizer.transform(X_test_txt)
+
+    Xtr_hand = handcrafted_feature_matrix(X_train_txt, SQL_KEYWORDS)
+    Xte_hand = handcrafted_feature_matrix(X_test_txt, SQL_KEYWORDS)
+
+    X_train = hstack([Xtr_tfidf, Xtr_hand])
+    X_test = hstack([Xte_tfidf, Xte_hand])
+
+    clf = RandomForestClassifier(n_estimators=200, random_state=42)
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+
+    print("SQL Injection Detection")
+    print(f"Accuracy: {accuracy_score(y_test, y_pred):.3f}")
+    print(classification_report(y_test, y_pred, target_names=["benign", "malicious"]))
+    print("Confusion matrix [[TN FP][FN TP]]:")
+    print(confusion_matrix(y_test, y_pred))
+
+    print("\nTest Samples")
+    samples = [
+        "' OR '1'='1' --",
+        "jane.doe@example.com",
+        "1; DROP TABLE orders;--",
+        "search: blue running shoes size 10",
+    ]
+    Xd_tfidf = vectorizer.transform(samples)
+    Xd_hand = handcrafted_feature_matrix(samples, SQL_KEYWORDS)
+    Xd = hstack([Xd_tfidf, Xd_hand])
+    preds = clf.predict(Xd)
+    for text, label in zip(samples, preds):
+        verdict = "MALICIOUS" if label == 1 else "benign"
+        print(f"[{verdict}] {text}")
+
+
+if __name__ == "__main__":
+    joblib.dump(vectorizer, "sqli_vectorizer.joblib")
+    joblib.dump(clf, "sqli_classifier.joblib")
+    print("\nSaved model artifacts. Run: python test_model.py")
+    main()