aiwaf 0.1.2__py3-none-any.whl → 0.1.5__py3-none-any.whl

aiwaf/middleware.py

@@ -1,54 +1,104 @@
+# aiwaf/middleware.py
+
 import time
+import re
+import os
 import numpy as np
 import joblib
+
 from collections import defaultdict
 from django.utils.deprecation import MiddlewareMixin
 from django.http import JsonResponse
 from django.conf import settings
 from django.core.cache import cache
-from django.urls import resolve
+from django.db.models import F
 from django.apps import apps
-from .blacklist_manager import BlacklistManager
+from django.urls import get_resolver
 
-try:
-    MODEL_PATH = settings.AIWAF_MODEL_PATH
-except AttributeError:
-    import importlib.resources
-    MODEL_PATH = importlib.resources.files("aiwaf").joinpath("resources/model.pkl")
+from .blacklist_manager import BlacklistManager
+from .models import DynamicKeyword
 
+MODEL_PATH = getattr(
+    settings,
+    "AIWAF_MODEL_PATH",
+    os.path.join(os.path.dirname(__file__), "resources", "model.pkl")
+)
 MODEL = joblib.load(MODEL_PATH)
 
+STATIC_KW = getattr(
+    settings,
+    "AIWAF_MALICIOUS_KEYWORDS",
+    [
+        ".php", "xmlrpc", "wp-", ".env", ".git", ".bak",
+        "conflg", "shell", "filemanager"
+    ]
+)
+
 def get_ip(request):
     xff = request.META.get("HTTP_X_FORWARDED_FOR")
     if xff:
         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)
 
 
 class RateLimitMiddleware:
-    WINDOW = getattr(settings, "AIWAF_RATE_WINDOW", 10)
-    MAX = getattr(settings, "AIWAF_RATE_MAX", 20)
-    FLOOD = getattr(settings, "AIWAF_RATE_FLOOD", 10)
+    WINDOW = 10
+    MAX    = 20
+    FLOOD  = 10
+
     def __init__(self, get_response):
         self.get_response = get_response
         self.logs = defaultdict(list)
+
     def __call__(self, request):
-        ip = get_ip(request)
+        ip  = get_ip(request)
         now = time.time()
         recs = [t for t in self.logs[ip] if now - t < self.WINDOW]
         recs.append(now)
         self.logs[ip] = recs
+
         if len(recs) > self.MAX:
             return JsonResponse({"error": "too_many_requests"}, status=429)
         if len(recs) > self.FLOOD:
@@ -59,40 +109,57 @@ class RateLimitMiddleware:
 
 
 class AIAnomalyMiddleware(MiddlewareMixin):
-    WINDOW_SECONDS = getattr(settings, "AIWAF_WINDOW_SECONDS", 60)
+    WINDOW = getattr(settings, "AIWAF_WINDOW_SECONDS", 60)
+    TOP_N  = getattr(settings, "AIWAF_DYNAMIC_TOP_N", 10)
+
     def process_request(self, request):
         ip = get_ip(request)
         if BlacklistManager.is_blocked(ip):
             return JsonResponse({"error": "blocked"}, status=403)
+
         now = time.time()
         key = f"aiwaf:{ip}"
         data = cache.get(key, [])
+        # TODO: you may want to capture real status & response_time in process_response
         data.append((now, request.path, 0, 0.0))
-        data = [d for d in data if now - d[0] < self.WINDOW_SECONDS]
-        cache.set(key, data, timeout=self.WINDOW_SECONDS)
+        data = [d for d in data if now - d[0] < self.WINDOW]
+        cache.set(key, data, timeout=self.WINDOW)
+
+        # update dynamic‐keyword counts
+        for seg in re.split(r"\W+", request.path.lower()):
+            if len(seg) > 3:
+                obj, _ = DynamicKeyword.objects.get_or_create(keyword=seg)
+                DynamicKeyword.objects.filter(pk=obj.pk).update(count=F("count") + 1)
+
         if len(data) < 5:
             return None
-        total = len(data)
-        ratio_404 = sum(1 for (_, _, st, _) in data if st == 404) / total
-        hits = sum(
-            any(k in path.lower() for k in settings.AIWAF_MALICIOUS_KEYWORDS)
-            for (_, path, _, _) in data
+
+        # pull top‐N dynamic tokens
+        top_dynamic = list(
+            DynamicKeyword.objects
+            .order_by("-count")
+            .values_list("keyword", flat=True)[: self.TOP_N]
         )
-        avg_rt = np.mean([rt for (_, _, _, rt) in data]) if data else 0.0
-        intervals = [
-            data[i][0] - data[i-1][0] for i in range(1, total)
-        ]
-        avg_iv = np.mean(intervals) if intervals else 0.0
-        X = np.array([[total, ratio_404, hits, avg_rt, avg_iv]], dtype=float)
+        ALL_KW = set(STATIC_KW) | set(top_dynamic)
+
+        total    = len(data)
+        ratio404 = sum(1 for (_, _, st, _) in data if st == 404) / total
+        hits     = sum(any(kw in path.lower() for kw in ALL_KW) for (_, path, _, _) in data)
+        avg_rt   = np.mean([rt for (_, _, _, rt) in data]) if data else 0.0
+        ivs      = [data[i][0] - data[i - 1][0] for i in range(1, total)]
+        avg_iv   = np.mean(ivs) if ivs else 0.0
+
+        X = np.array([[total, ratio404, hits, avg_rt, avg_iv]], dtype=float)
         if MODEL.predict(X)[0] == -1:
             BlacklistManager.block(ip, "AI anomaly")
             return JsonResponse({"error": "blocked"}, status=403)
+
         return None
 
 
 class HoneypotMiddleware(MiddlewareMixin):
     def process_view(self, request, view_func, view_args, view_kwargs):
-        trap = request.POST.get(settings.AIWAF_HONEYPOT_FIELD, "")
+        trap = request.POST.get(getattr(settings, "AIWAF_HONEYPOT_FIELD", "hp_field"), "")
         if trap:
             ip = get_ip(request)
             BlacklistManager.block(ip, "HONEYPOT triggered")
@@ -105,11 +172,13 @@ class UUIDTamperMiddleware(MiddlewareMixin):
         uid = view_kwargs.get("uuid")
         if not uid:
             return None
+
         ip = get_ip(request)
-        app_label = view_kwargs.get("app_label") or view_func.__module__.split('.')[0]
-        app_config = apps.get_app_config(app_label)
-        for Model in app_config.get_models():
+        app_label = view_func.__module__.split(".")[0]
+        app_cfg   = apps.get_app_config(app_label)
+        for Model in app_cfg.get_models():
             if Model.objects.filter(pk=uid).exists():
                 return None
+
         BlacklistManager.block(ip, "UUID tampering")
-        return JsonResponse({"error": "blocked"}, status=403)
+        return JsonResponse({"error": "blocked"}, status=403)

aiwaf/models.py

@@ -26,3 +26,11 @@ class BlacklistEntry(models.Model):
 
     def __str__(self):
         return f"{self.ip_address} ({self.reason})"
+
+class DynamicKeyword(models.Model):
+    keyword      = models.CharField(max_length=100, unique=True)
+    count        = models.PositiveIntegerField(default=0)
+    last_updated = models.DateTimeField(auto_now=True)
+
+    class Meta:
+        ordering = ['-count']

aiwaf/trainer.py

@@ -1,44 +1,48 @@
-# aiwaf/trainer.py
-
 import os
 import glob
 import gzip
 import re
-import joblib
 from datetime import datetime
-from collections import defaultdict
-from .models import BlacklistEntry
+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
+
+LOG_PATH = settings.AIWAF_ACCESS_LOG
+MODEL_PATH = os.path.join(os.path.dirname(__file__), "resources", "model.pkl")
+
+STATIC_KW = [".php", "xmlrpc", "wp-", ".env", ".git", ".bak", "conflg", "shell", "filemanager"]
+STATUS_IDX = ["200", "403", "404", "500"]
 
-LOG_PATH   = settings.AIWAF_ACCESS_LOG
-MODEL_PATH = os.path.join(
-    os.path.dirname(__file__),
-    "resources",
-    "model.pkl"
-)
-MALICIOUS_KEYWORDS = [".php", "xmlrpc", "wp-", ".env", ".git", ".bak", "conflg", "shell", "filemanager"]
-STATUS_CODES       = ["200", "403", "404", "500"]
 _LOG_RX = re.compile(
-    r'(\d+\.\d+\.\d+\.\d+).*\[(.*?)\].*"(?:GET|POST) (.*?) HTTP/.*?" (\d{3}).*?"(.*?)" "(.*?)".*?response-time=(\d+\.\d+)'
+    r'(\d+\.\d+\.\d+\.\d+).*\[(.*?)\].*"(?:GET|POST) (.*?) HTTP/.*?" '
+    r'(\d{3}).*?"(.*?)" "(.*?)".*?response-time=(\d+\.\d+)'
 )
-BlacklistedIP = BlacklistEntry.objects.all()
+
+BlacklistEntry = apps.get_model("aiwaf", "BlacklistEntry")
+DynamicKeyword = apps.get_model("aiwaf", "DynamicKeyword")
+
+
 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:
@@ -59,14 +63,14 @@ def _parse(line):
 
 
 def train():
-    raw = _read_all_logs()
-    if not raw:
-        print("No log lines found – check 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)
+    ip_404 = defaultdict(int)
     ip_times = defaultdict(list)
-    for ln in raw:
+    for ln in raw_lines:
         rec = _parse(ln)
         if not rec:
             continue
@@ -74,7 +78,7 @@ def train():
         ip_times[rec["ip"]].append(rec["timestamp"])
         if rec["status"] == "404":
             ip_404[rec["ip"]] += 1
-    blocked = []
+    blocked_404 = []
     for ip, count in ip_404.items():
         if count >= 6:
             obj, created = BlacklistEntry.objects.get_or_create(
@@ -82,42 +86,66 @@ def train():
                 defaults={"reason": "Excessive 404s (≥6)"}
             )
             if created:
-                blocked.append(ip)
-    if blocked:
-        print(f"Auto‑blocked {len(blocked)} IPs for ≥6 404s: {', '.join(blocked)}")
-    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)
-    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 and saved to {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}")
+
+    tokens = Counter()
+    for r in parsed:
+        if r["status"].startswith(("4", "5")):
+            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]}")
+
 
+if __name__ == "__main__":
+    train()

aiwaf-0.1.5.dist-info/METADATA

@@ -0,0 +1,195 @@
+Metadata-Version: 2.4
+Name: aiwaf
+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 
+
+> 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.
+
+---
+
+## Package Structure
+
+```
+aiwaf/
+├── __init__.py
+├── blacklist_manager.py
+├── middleware.py
+├── trainer.py                   # exposes train()
+├── utils.py
+├── template_tags/
+│   └── aiwaf_tags.py
+├── resources/
+│   ├── model.pkl                # pre‑trained base model
+│   └── dynamic_keywords.json    # evolves daily
+├── management/
+│   └── commands/
+│       └── detect_and_train.py  # `python manage.py detect_and_train`
+└── LICENSE
+```
+
+---
+
+## Features
+
+- **IP Blocklist**  
+  Instantly blocks suspicious IPs (supports CSV fallback or Django model).
+
+- **Rate Limiting**  
+  Sliding‑window blocks flooders (> `AIWAF_RATE_MAX` per `AIWAF_RATE_WINDOW`), then blacklists them.
+
+- **AI Anomaly Detection**  
+  IsolationForest on features:
+  - Path length  
+  - Keyword hits (static + dynamic)  
+  - Response time  
+  - Status‑code index  
+  - Burst count  
+  - Total 404s  
+
+- **Dynamic Keyword Extraction**  
+  Every retrain: top 10 most frequent “words” from 4xx/5xx paths are appended to your malicious keyword set.
+
+- **File‑Extension Probing Detection**  
+  Tracks repeated 404s on common web‑extensions (e.g. `.php`, `.asp`) and auto‑blocks after a burst.
+
+- **Honeypot Field**  
+  Hidden form field (via template tag) that bots fill → instant block.
+
+- **UUID Tampering Protection**  
+  Any `<uuid:…>` URL that doesn’t map to **any** model in its Django app gets blocked.
+
+- **Daily Retraining**  
+  Reads rotated/gzipped logs, auto‑blocks 404 floods (≥6), retrains the model, updates `model.pkl` + `dynamic_keywords.json`.
+
+---
+
+## Installation
+
+```bash
+# From PyPI
+pip install aiwaf
+
+# Or for local development
+git clone https://github.com/aayushgauba/aiwaf.git
+cd aiwaf
+pip install -e .
+```
+
+---
+
+## ⚙️ Configuration (`settings.py`)
+
+```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"
+
+# Optional (defaults shown)
+AIWAF_MODEL_PATH         = BASE_DIR / "aiwaf" / "resources" / "model.pkl"
+AIWAF_HONEYPOT_FIELD     = "hp_field"
+AIWAF_RATE_WINDOW        = 10         # seconds
+AIWAF_RATE_MAX           = 20         # max reqs/window
+AIWAF_RATE_FLOOD         = 10         # flood threshold
+AIWAF_WINDOW_SECONDS     = 60         # anomaly window
+AIWAF_FILE_EXTENSIONS    = [".php", ".asp", ".jsp"]  # 404‑burst tracked extensions
+```
+
+> **Note:** You no longer need to define `AIWAF_MALICIOUS_KEYWORDS` or `AIWAF_STATUS_CODES` in your settings — they’re built in and evolve dynamically.
+
+---
+
+## Middleware Setup
+
+Add in **this** order to your `MIDDLEWARE` list:
+
+```python
+MIDDLEWARE = [
+    "aiwaf.middleware.IPBlockMiddleware",
+    "aiwaf.middleware.RateLimitMiddleware",
+    "aiwaf.middleware.AIAnomalyMiddleware",
+    "aiwaf.middleware.HoneypotMiddleware",
+    "aiwaf.middleware.UUIDTamperMiddleware",
+    # ... other middleware ...
+]
+```
+
+---
+
+## Honeypot Field (in your template)
+
+```django
+{% load aiwaf_tags %}
+
+<form method="post">
+  {% csrf_token %}
+  {% honeypot_field %}
+  <!-- your real fields -->
+</form>
+```
+
+> Renders a hidden `<input name="hp_field" style="display:none">`.  
+> Any non‑empty submission → IP blacklisted.
+
+---
+
+## Running Detection & Training
+
+```bash
+python manage.py detect_and_train
+```
+
+**What happens:**
+1. Read access logs
+2. Auto‑block IPs with ≥ 6 total 404s
+3. Extract features & train IsolationForest
+4. Save `model.pkl`
+5. Extract top 10 dynamic keywords from 4xx/5xx
+
+---
+
+## How It Works
+
+| 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    |
+
+---
+
+## License
+
+This project is licensed under the **MIT License**. See the [LICENSE](LICENSE) file for details.
+
+---
+
+## Credits
+
+**AI‑WAF** by [Aayush Gauba](https://github.com/aayushgauba)  
+> “Let your firewall learn and evolve — keep your site a fortress.”

{aiwaf-0.1.2.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=WHoXMtKZ_WpueSPylH4XXpKzM9-cqPDunDM0fuklzg0,4220
-aiwaf/models.py,sha256=GTojMOZ3M5pDDNmpU4o353M3w59jEclzHqJgofHzfBA,1021
+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=8eLrq3bOmRle4KDRWnzxnc-Gv6oo5IErqoDGO_v_qG4,3629
+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-0.1.2.dist-info/METADATA,sha256=htVp1TT0tRdAFDIxC1mjv6opQMQIHy8MhHPv0NDPIp4,4396
-aiwaf-0.1.2.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-aiwaf-0.1.2.dist-info/top_level.txt,sha256=kU6EyjobT6UPCxuWpI_BvcHDG0I2tMgKaPlWzVxe2xI,6
-aiwaf-0.1.2.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.

aiwaf-0.1.2.dist-info/METADATA

@@ -1,187 +0,0 @@
-Metadata-Version: 2.4
-Name: aiwaf
-Version: 0.1.2
-Summary: AI-powered Web Application Firewall
-Author: Aayush Gauba
-Author-email: Aayush Gauba <gauba.aayush@gmail.com>
-License: MIT
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-Dynamic: author
-
-# AI‑WAF
-
-> A self-learning, Django-friendly Web Application Firewall  
-> with rate-limiting, anomaly detection, honeypots, UUID-tamper protection, and daily retraining.
-
----
-
-## Package Structure
-
-```
-aiwaf/
-├── __init__.py
-├── blacklist_manager.py
-├── middleware.py
-├── trainer.py                   # exposes detect_and_train()
-├── utils.py
-├── template_tags/
-│   └── aiwaf_tags.py
-├── resources/
-│   └── model.pkl                # pre-trained base model
-├── management/
-│   └── commands/
-│       └── detect_and_train.py  # python manage.py detect_and_train
-└── LICENSE
-```
-
----
-
-## Features
-
-- **IP Blocklist**  
-  Automatically blocks suspicious IPs; optionally backed by CSV or Django model.
-
-- **Rate Limiting**  
-  Sliding window logic blocks IPs exceeding a threshold of requests per second.
-
-- **AI Anomaly Detection**  
-  IsolationForest trained on real logs with features like:
-  - Path length
-  - Keyword hits
-  - Response time
-  - Status code index
-  - Burst count
-  - Total 404s
-
-- **Honeypot Field**  
-  Hidden form field that bots are likely to fill — if triggered, the IP is blocked.
-
-- **UUID Tampering Protection**  
-  Detects if someone is probing by injecting random/nonexistent UUIDs into URLs.
-
-- **Daily Retraining**  
-  A single command retrains your model every day based on your logs.
-
----
-
-## Installation
-
-Install locally or from PyPI:
-
-```bash
-pip install aiwaf
-```
-
-Or for local dev:
-
-```bash
-git clone https://github.com/aayushgauba/aiwaf.git
-cd aiwaf
-pip install -e .
-```
-
----
-
-## ⚙️ Configuration (`settings.py`)
-
-```python
-INSTALLED_APPS += [
-    "aiwaf",
-]
-
-# Required
-AIWAF_ACCESS_LOG = "/var/log/nginx/access.log"
-
-# Optional (defaults included)
-AIWAF_MODEL_PATH = BASE_DIR / "aiwaf" / "resources" / "model.pkl"
-AIWAF_MALICIOUS_KEYWORDS = [".php", "xmlrpc", "wp-", ".env", ".git", ".bak", "conflg", "shell", "filemanager"]
-AIWAF_STATUS_CODES = ["200", "403", "404", "500"]
-AIWAF_HONEYPOT_FIELD = "hp_field"
-```
-
----
-
-## Middleware Setup
-
-Add to `MIDDLEWARE` in order:
-
-```python
-MIDDLEWARE = [
-    "aiwaf.middleware.IPBlockMiddleware",
-    "aiwaf.middleware.RateLimitMiddleware",
-    "aiwaf.middleware.AIAnomalyMiddleware",
-    "aiwaf.middleware.HoneypotMiddleware",
-    "aiwaf.middleware.UUIDTamperMiddleware",
-    ...
-]
-```
-
----
-
-## Honeypot Field (in template)
-
-```html
-{% load aiwaf_tags %}
-
-<form method="post">
-  {% csrf_token %}
-  {% honeypot_field %}
-  <!-- other fields -->
-</form>
-```
-
-The hidden field will be `<input type="hidden" name="hp_field">`.  
-If it’s ever filled → IP gets blocked.
-
----
-
-##  Run Detection + Training
-
-```bash
-python manage.py detect_and_train
-```
-
-What it does:
-
-- Reads logs (supports `.gz` and rotated logs).
-- Detects excessive 404s (≥6) → instant block.
-- Builds feature vectors from logs.
-- Trains IsolationForest and saves `model.pkl`.
-
-Schedule it to run daily via `cron`, `Celery beat`, or systemd timer.
-
----
-
-## How It Works (Simplified)
-
-| Middleware             | Functionality                                                |
-|------------------------|--------------------------------------------------------------|
-| IPBlockMiddleware      | Blocks requests from known blacklisted IPs                   |
-| RateLimitMiddleware    | Blocks flooders (>20/10s) and blacklists them (>10/10s)      |
-| AIAnomalyMiddleware    | Uses ML to detect suspicious behavior in request patterns    |
-| HoneypotMiddleware     | Detects bots filling hidden inputs in forms                  |
-| UUIDTamperMiddleware   | Detects guessing/probing by checking invalid UUID access     |
-
----
-
-## Development Roadmap
-
-- [ ] Add CSV blocklist fallback
-- [ ] Admin dashboard integration
-- [ ] Auto-pruning of old block entries
-- [ ] Real-time log streaming compatibility
-- [ ] Docker/Helm deployment guide
-
----
-
-##  License
-
-This project is licensed under the **MIT License** — see `LICENSE` for details.
-
----
-
-## Credits
-
-**AIWAF** by [Aayush Gauba](https://github.com/aayushgauba)  
-> "Let your firewall learn and evolve with your logs. Make your site a fortress."