-
Notifications
You must be signed in to change notification settings - Fork 1
Detection Engines
Emirhan Uçan edited this page Jul 17, 2026
·
13 revisions
HydraDragonAV Mobile combines multiple scanning technologies to achieve comprehensive Android malware detection.
-
Engine: Custom YARA-X fork with the
hydradragonandandroguardmodules. -
Modules: The
hydradragonmodule provides per-app DNS/connection attribution (Android 10+). Theandroguardmodule provides APK-specific analysis features. - Rules: Extensive collection of YARA rules targeting Android malware families.
- Method: Pattern-based rule matching with conditions and metadata.
-
Auto-generated rules: The native engine generates yarGen-style rules for confirmed malware, using AND-based multi-condition logic — package name (OR'd if multiple), DEX string pool threshold, and
androguard.rootkit_behavior()— so all signals must align to match, reducing FPs.
-
Integration:
libclamavsignatures compiled into the native Rust engine. -
Database: Filtered by
clam_juice.pyto keep only Android-relevant platforms (Andr, Unix, Linux, Email, PUA) plus all Phishing signatures. Windows/OSX/Java signatures are excluded. - Method: Signature-based pattern matching.
- File-type gate: Both ClamAV and YARA-X only run at all on a file confidently identified as APK/ZIP, DEX, ELF, HTML, ASCII text, PDF, or an image — desktop-only formats (PE, OLE2, Mail, Mach-O, SWF, Java) and files of an indeterminate type are skipped outright, not just rejected signature-by-signature. See ClamAV-Integration.
-
Engine: Pure-Rust TLSH implementation (
tlsh-rs). - Database: MalwareBazaar-derived TLSH digest database (APK/ELF/SO/DEX).
- Method: Compares scanned files against known-malware digests to find similar-but-not-identical samples.
- MinHash/LSH + Isolation Forest: Scores every scanned sample with a Jaccard similarity and anomaly score, flagging outliers that don't match any known-clean or known-malware profile.
- AIEngine: Lightweight logistic-regression classifier that scores DEX-level behavior — obfuscation, dynamic loading, crypto/socket/shell APIs, adware SDKs.
-
Method: Extracts every embedded
http(s)://URL from raw bytes of scanned files (APK or otherwise). - Filter: Checks extracted URLs against native malware/phishing URL XOR filters.
- Advantage: Full URL with path is far more specific than bare domain, reducing false positives.
- Dual layer: Binary-fuse XOR filter (in-memory, SHA-256 hashes) + SQLite database (full package metadata).
- Purpose: Known-good software is never flagged. See NSRL-Whitelisting.
- Engine: Unicorn CPU sandbox (ARM/ARM64/x86/x86_64).
-
Method: Runs embedded native library
JNI_OnLoad/entry code in a bounded, syscall-free environment. - Purpose: Reveals runtime-decoded strings (e.g., C2 URLs) that never appear in static analysis.
| Engine | Type | Speed | False Positives | Offline |
|---|---|---|---|---|
| YARA-X | Pattern Rules | Very Fast | Low-Medium | Yes |
| ClamAV | Signatures | Fast | Very Low | Yes |
| TLSH | Fuzzy Hash | Fast | Low | Yes |
| ML (Isolation Forest) | Anomaly Detection | Medium | Low | Yes |
| AIEngine | Logistic Regression | Fast | Low-Medium | Yes |
| URL Scanner | XOR Filter | Very Fast | Very Low | Yes |
| Unicorn | CPU Emulation | Slow | Low | Yes |
┌─────────────────────────────────────────────────────────────┐
│ File / APK Scan Request │
└────────────────────────┬────────────────────────────────────┘
│
┌────▼────┐
│ NSRL │
│ Whitelist│
└────┬────┘
│ (if not whitelisted)
┌────▼────┐
│ ML │
│ Score │
└────┬────┘
┌──────┴──────┐
│ │
confident benign uncertain/malicious
│ │
│ ┌────▼────┐ ┌────▼────┐
│ │ YARA-X │ │ ClamAV │
│ │ Scan │ │ Scan │
│ └────┬────┘ └────┬────┘
│ │ │
│ ┌────▼────┐ ┌────▼────┐
│ │ TLSH │ │Unicorn │
│ │ Match │ │Emulation│
│ └────┬────┘ └────┬────┘
│ │ │
┌───────┼─────────────┼─────────────┘
│ │ │
┌────▼────┐ │ ┌────▼────┐
│ Clean │ │ │Malicious│
│ Allow │ │ │ Action │
└─────────┘ │ └─────────┘
│
│ (suspicious alerts
│ from AIEngine)
- YARA-X-Usage — YARA-X rule management
- ClamAV-Integration — ClamAV setup
- AI-ML-Models — ML model details
- Ransomware-Defense — Ransomware protection
- NSRL-Whitelisting — Whitelist architecture