aiwaf 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

aiwaf/middleware.py

@@ -13,11 +13,11 @@ from django.conf import settings
 from django.core.cache import cache
 from django.db.models import F
 from django.apps import apps
+from django.urls import get_resolver
 
 from .blacklist_manager import BlacklistManager
 from .models import DynamicKeyword
 
-# ─── Model loading with fallback ────────────────────────────────────────────
 MODEL_PATH = getattr(
     settings,
     "AIWAF_MODEL_PATH",
@@ -25,7 +25,6 @@ MODEL_PATH = getattr(
 )
 MODEL = joblib.load(MODEL_PATH)
 
-# ─── Static keywords default ────────────────────────────────────────────────
 STATIC_KW = getattr(
     settings,
     "AIWAF_MALICIOUS_KEYWORDS",
@@ -41,15 +40,46 @@ def get_ip(request):
         return xff.split(",")[0].strip()
     return request.META.get("REMOTE_ADDR", "")
 
-
-class IPBlockMiddleware:
+class IPAndKeywordBlockMiddleware:
     def __init__(self, get_response):
         self.get_response = get_response
+        self.url_patterns = self._collect_view_paths()
+
+    def _collect_view_paths(self):
+        resolver = get_resolver()
+        patterns = set()
+
+        def extract(patterns_list, prefix=""):
+            for p in patterns_list:
+                if hasattr(p, "url_patterns"):
+                    extract(p.url_patterns, prefix + str(p.pattern))
+                else:
+                    pat = (prefix + str(p.pattern)).strip("^$")
+                    patterns.add(pat)
+        extract(resolver.url_patterns)
+        return patterns
 
     def __call__(self, request):
         ip = get_ip(request)
+        path = request.path.lower()
         if BlacklistManager.is_blocked(ip):
             return JsonResponse({"error": "blocked"}, status=403)
+        segments = [seg for seg in re.split(r"\W+", path) if len(seg) > 3]
+        for seg in segments:
+            obj, _ = DynamicKeyword.objects.get_or_create(keyword=seg)
+            DynamicKeyword.objects.filter(pk=obj.pk).update(count=F("count") + 1)
+        dynamic_top = list(
+            DynamicKeyword.objects
+            .order_by("-count")
+            .values_list("keyword", flat=True)[: getattr(settings, "AIWAF_DYNAMIC_TOP_N", 10)]
+        )
+        all_kw = set(STATIC_KW) | set(dynamic_top)
+        safe_kw = {kw for kw in all_kw if any(kw in pat for pat in self.url_patterns)}
+        suspicious_kw = all_kw - safe_kw
+        for seg in segments:
+            if seg in suspicious_kw:
+                BlacklistManager.block(ip, f"Keyword block: {seg}")
+                return JsonResponse({"error": "blocked"}, status=403)
         return self.get_response(request)
 
 

aiwaf/trainer.py

@@ -2,63 +2,47 @@ import os
 import glob
 import gzip
 import re
-import json
-import joblib
-
 from datetime import datetime
 from collections import defaultdict, Counter
 
 import pandas as pd
 from sklearn.ensemble import IsolationForest
+import joblib
 
 from django.conf import settings
 from django.apps import apps
+from django.db.models import F
 
-# ─── CONFIG ────────────────────────────────────────────────────────────────
-
-# Where to read your access logs (and rotated/.gz siblings)
 LOG_PATH = settings.AIWAF_ACCESS_LOG
+MODEL_PATH = os.path.join(os.path.dirname(__file__), "resources", "model.pkl")
 
-# Where we save our trained model
-MODEL_PATH = os.path.join(
-    os.path.dirname(__file__),
-    "resources",
-    "model.pkl"
-)
-
-# Static “malicious” path keywords & file extensions
-MALICIOUS_KEYWORDS = [
-    ".php", "xmlrpc", "wp-", ".env", ".git", ".bak",
-    "conflg", "shell", "filemanager"
-]
-STATUS_CODES = ["200", "403", "404", "500"]
+STATIC_KW = [".php", "xmlrpc", "wp-", ".env", ".git", ".bak", "conflg", "shell", "filemanager"]
+STATUS_IDX = ["200", "403", "404", "500"]
 
-# Regex for combined log with response-time=…
 _LOG_RX = re.compile(
     r'(\d+\.\d+\.\d+\.\d+).*\[(.*?)\].*"(?:GET|POST) (.*?) HTTP/.*?" '
     r'(\d{3}).*?"(.*?)" "(.*?)".*?response-time=(\d+\.\d+)'
 )
 
-# Your Django model for storing blocked IPs
 BlacklistEntry = apps.get_model("aiwaf", "BlacklistEntry")
+DynamicKeyword = apps.get_model("aiwaf", "DynamicKeyword")
 
 
-# ─── READ & PARSE LOG LINES ─────────────────────────────────────────────────
-
 def _read_all_logs():
     lines = []
     if LOG_PATH and os.path.exists(LOG_PATH):
         with open(LOG_PATH, "r", errors="ignore") as f:
-            lines += f.readlines()
-    for path in sorted(glob.glob(LOG_PATH + ".*")):
+            lines.extend(f.readlines())
+    for path in sorted(glob.glob(f"{LOG_PATH}.*")):
         opener = gzip.open if path.endswith(".gz") else open
         try:
             with opener(path, "rt", errors="ignore") as f:
-                lines += f.readlines()
+                lines.extend(f.readlines())
         except OSError:
             continue
     return lines
 
+
 def _parse(line):
     m = _LOG_RX.search(line)
     if not m:
@@ -78,20 +62,15 @@ def _parse(line):
     }
 
 
-# ─── TRAIN ENTRYPOINT ───────────────────────────────────────────────────────
-
 def train():
-    raw = _read_all_logs()
-    if not raw:
-        print("❌ No log lines found – check settings.AIWAF_ACCESS_LOG")
+    raw_lines = _read_all_logs()
+    if not raw_lines:
+        print(" No log lines found – check AIWAF_ACCESS_LOG setting.")
         return
-
-    parsed  = []
-    ip_404   = defaultdict(int)
+    parsed = []
+    ip_404 = defaultdict(int)
     ip_times = defaultdict(list)
-
-    # parse + accumulate timestamps & 404 counts
-    for ln in raw:
+    for ln in raw_lines:
         rec = _parse(ln)
         if not rec:
             continue
@@ -99,77 +78,74 @@ def train():
         ip_times[rec["ip"]].append(rec["timestamp"])
         if rec["status"] == "404":
             ip_404[rec["ip"]] += 1
-
-    # auto-block IPs with >=6 total 404s
-    newly_blocked = []
-    for ip, cnt in ip_404.items():
-        if cnt >= 6:
+    blocked_404 = []
+    for ip, count in ip_404.items():
+        if count >= 6:
             obj, created = BlacklistEntry.objects.get_or_create(
                 ip_address=ip,
                 defaults={"reason": "Excessive 404s (≥6)"}
             )
             if created:
-                newly_blocked.append(ip)
-    if newly_blocked:
-        print(f"🔒 Blocked {len(newly_blocked)} IPs for 404 flood: {newly_blocked}")
-
-    # build feature vectors
-    rows = []
+                blocked_404.append(ip)
+    if blocked_404:
+        print(f"Blocked {len(blocked_404)} IPs for 404 flood: {blocked_404}")
+    feature_dicts = []
     for r in parsed:
-        ip         = r["ip"]
-        burst      = sum(
+        ip = r["ip"]
+        burst = sum(
             1 for t in ip_times[ip]
             if (r["timestamp"] - t).total_seconds() <= 10
         )
-        total404   = ip_404[ip]
-        kw_hits    = sum(k in r["path"].lower() for k in MALICIOUS_KEYWORDS)
-        status_idx = STATUS_CODES.index(r["status"]) if r["status"] in STATUS_CODES else -1
-
-        rows.append([
-            len(r["path"]),
-            kw_hits,
-            r["response_time"],
-            status_idx,
-            burst,
-            total404
-        ])
-
-    if not rows:
-        print("⚠️ No entries to train on.")
+        total404 = ip_404[ip]
+        kw_hits = sum(k in r["path"].lower() for k in STATIC_KW)
+        status_idx = STATUS_IDX.index(r["status"]) if r["status"] in STATUS_IDX else -1
+        feature_dicts.append({
+            "ip": ip,
+            "path_len": len(r["path"]),
+            "kw_hits": kw_hits,
+            "resp_time": r["response_time"],
+            "status_idx": status_idx,
+            "burst_count": burst,
+            "total_404": total404,
+        })
+
+    if not feature_dicts:
+        print("⚠️ Nothing to train on – no valid log entries.")
         return
 
-    df = pd.DataFrame(
-        rows,
-        columns=[
-            "path_len", "kw_hits", "resp_time",
-            "status_idx", "burst_count", "total_404"
-        ]
-    ).fillna(0).astype(float)
-
-    # train & save
-    clf = IsolationForest(contamination=0.01, random_state=42)
-    clf.fit(df.values)
+    df = pd.DataFrame(feature_dicts)
+    feature_cols = [c for c in df.columns if c != "ip"]
+    X = df[feature_cols].astype(float).values
+    model = IsolationForest(contamination=0.01, random_state=42)
+    model.fit(X)
     os.makedirs(os.path.dirname(MODEL_PATH), exist_ok=True)
-    joblib.dump(clf, MODEL_PATH)
-    print(f"✅ Model trained on {len(df)} samples → {MODEL_PATH}")
+    joblib.dump(model, MODEL_PATH)
+    print(f"✅ Model trained on {len(X)} samples → {MODEL_PATH}")
+    preds = model.predict(X)  # -1 for outliers
+    anomalous_ips = set(df.loc[preds == -1, 'ip'])
+    blocked_anom = []
+    for ip in anomalous_ips:
+        obj, created = BlacklistEntry.objects.get_or_create(
+            ip_address=ip,
+            defaults={"reason": "Anomalous behavior"}
+        )
+        if created:
+            blocked_anom.append(ip)
+    if blocked_anom:
+        print(f" Blocked {len(blocked_anom)} anomalous IPs: {blocked_anom}")
 
-    # extract top‑10 dynamic keywords from 4xx/5xx paths
     tokens = Counter()
     for r in parsed:
         if r["status"].startswith(("4", "5")):
-            segs = re.split(r"\W+", r["path"].lower())
-            for seg in segs:
-                if len(seg) > 3 and seg not in MALICIOUS_KEYWORDS:
+            for seg in re.split(r"\W+", r["path"].lower()):
+                if len(seg) > 3 and seg not in STATIC_KW:
                     tokens[seg] += 1
+    top_tokens = tokens.most_common(10)
+    for kw, cnt in top_tokens:
+        obj, _ = DynamicKeyword.objects.get_or_create(keyword=kw)
+        DynamicKeyword.objects.filter(pk=obj.pk).update(count=F("count") + cnt)
+    print(f"DynamicKeyword DB updated with top tokens: {[kw for kw, _ in top_tokens]}")
 
-    new_kw = [kw for kw, _ in tokens.most_common(10)]
-    DK_FILE = os.path.join(os.path.dirname(__file__), "resources", "dynamic_keywords.json")
-    try:
-        existing = set(json.load(open(DK_FILE)))
-    except FileNotFoundError:
-        existing = set()
-    updated = sorted(existing | set(new_kw))
-    with open(DK_FILE, "w") as f:
-        json.dump(updated, f, indent=2)
-
-    print(f"📝 Updated dynamic keywords: {new_kw}")
+
+if __name__ == "__main__":
+    train()

{aiwaf-0.1.3.dist-info → aiwaf-0.1.5.dist-info}/METADATA

@@ -1,15 +1,21 @@
 Metadata-Version: 2.4
 Name: aiwaf
-Version: 0.1.3
+Version: 0.1.5
 Summary: AI-powered Web Application Firewall
+Home-page: https://github.com/aayushgauba/aiwaf
 Author: Aayush Gauba
 Author-email: Aayush Gauba <gauba.aayush@gmail.com>
 License: MIT
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
+License-File: LICENSE
 Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
 
-# AI‑WAF
+
+# AI‑WAF 
 
 > A self‑learning, Django‑friendly Web Application Firewall  
 > with rate‑limiting, anomaly detection, honeypots, UUID‑tamper protection, dynamic keyword extraction, file‑extension probing detection, and daily retraining.
@@ -91,6 +97,14 @@ pip install -e .
 ```python
 INSTALLED_APPS += ["aiwaf"]
 
+### Database Setup
+
+After adding `aiwaf` to your `INSTALLED_APPS`, create the necessary tables for the IP‐blacklist and dynamic‐keyword models:
+
+```bash
+python manage.py makemigrations aiwaf
+python manage.py migrate
+
 # Required
 AIWAF_ACCESS_LOG = "/var/log/nginx/access.log"
 
@@ -159,13 +173,13 @@ python manage.py detect_and_train
 
 ## How It Works
 
-| Middleware               | Purpose                                                         |
-|--------------------------|------------------------------------------------------------------|
-| IPBlockMiddleware        | Blocks requests from known blacklisted IPs                      |
-| RateLimitMiddleware      | Enforces burst & flood thresholds                               |
-| AIAnomalyMiddleware      | ML‑driven behavior analysis + block on anomaly                  |
-| HoneypotMiddleware       | Detects bots filling hidden inputs in forms                     |
-| UUIDTamperMiddleware     | Blocks guessed/nonexistent UUIDs across all models in an app    |
+| Middleware                         | Purpose                                                         |
+|------------------------------------|-----------------------------------------------------------------|
+| IPAndKeywordBlockMiddleware        | Blocks requests from known blacklisted IPs and Keywords         |
+| RateLimitMiddleware                | Enforces burst & flood thresholds                               |
+| AIAnomalyMiddleware                | ML‑driven behavior analysis + block on anomaly                  |
+| HoneypotMiddleware                 | Detects bots filling hidden inputs in forms                     |
+| UUIDTamperMiddleware               | Blocks guessed/nonexistent UUIDs across all models in an app    |
 
 ---
 

{aiwaf-0.1.3.dist-info → aiwaf-0.1.5.dist-info}/RECORD

@@ -1,10 +1,10 @@
 aiwaf/__init__.py,sha256=nQFpJ1YpX48snzLjEQCf8zD2YNh8v0b_kPTrXx8uBYc,46
 aiwaf/apps.py,sha256=nCez-Ptlv2kaEk5HenA8b1pATz1VfhrHP1344gwcY1A,142
 aiwaf/blacklist_manager.py,sha256=sM6uTH7zD6MOPGb0kzqV2aFut2vxKgft_UVeRJr7klw,392
-aiwaf/middleware.py,sha256=UIJ-1kA-NjKwpt3JS3vvsuhjaBXGliGt_4VKuL_OGq8,5254
+aiwaf/middleware.py,sha256=04AbNgkwLMaYSiuEtw59A-O02tt4cqaKmP7XDNlkIG0,6359
 aiwaf/models.py,sha256=8au1umopgCo0lthztTTRrYRJQUM7uX8eAeXgs3z45K4,1282
 aiwaf/storage.py,sha256=bxCILzzvA1-q6nwclRE8WrfoRhe25H4VrsQDf0hl_lY,1903
-aiwaf/trainer.py,sha256=8hU9k3bF_9QIkGix3TqFl7YuNeQV9dPriY2WhLo6s40,5411
+aiwaf/trainer.py,sha256=TKWJZzWTg892vdoSGWdCA0i-dKof2b29buWqJUrkr6k,4820
 aiwaf/utils.py,sha256=RkEUWhhHy6tOk7V0UYv3cN4xhOR_7aBy9bjhwuV2cdA,1436
 aiwaf/management/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aiwaf/management/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -12,7 +12,8 @@ aiwaf/management/commands/detect_and_train.py,sha256=-o-LZ7QZ5GeJPCekryox1DGXKMm
 aiwaf/resources/model.pkl,sha256=rCCXH38SJrnaOba2WZrU1LQVzWT34x6bTVkq20XJU-Q,1091129
 aiwaf/template_tags/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aiwaf/template_tags/aiwaf_tags.py,sha256=1KGqeioYmgKACDUiPkykSqI7DLQ6-Ypy1k00weWj9iY,399
-aiwaf-0.1.3.dist-info/METADATA,sha256=zgcejLdSfeE_bcqAvuebUJHN2ynKxtE24wVWdRdA_EA,4977
-aiwaf-0.1.3.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-aiwaf-0.1.3.dist-info/top_level.txt,sha256=kU6EyjobT6UPCxuWpI_BvcHDG0I2tMgKaPlWzVxe2xI,6
-aiwaf-0.1.3.dist-info/RECORD,,
+aiwaf-0.1.5.dist-info/licenses/LICENSE,sha256=Ir8PX4dxgAcdB0wqNPIkw84fzIIRKE75NoUil9RX0QU,1069
+aiwaf-0.1.5.dist-info/METADATA,sha256=g1hwdQBSJX1JBBnBim_TFtzjVMI5Ixl0WVrPPlnQCPg,5405
+aiwaf-0.1.5.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+aiwaf-0.1.5.dist-info/top_level.txt,sha256=kU6EyjobT6UPCxuWpI_BvcHDG0I2tMgKaPlWzVxe2xI,6
+aiwaf-0.1.5.dist-info/RECORD,,

aiwaf-0.1.5.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Aayush Gauba
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.