analyzing-typosquatting-domains-with-dnstwist

使用 DNSTwist 分析仿冒域名

概述

DNSTwist 是一个域名排列引擎，可生成外观相似的域名，用于检测仿冒域名、同形异义钓鱼攻击和品牌冒充。它通过字符替换、转置、插入、遗漏和同形字符替换等技术生成数千个域名排列，然后检查 DNS 记录（A、AAAA、NS、MX），使用模糊哈希（ssdeep）和感知哈希（pHash）计算网页相似度，并识别可能恶意的已注册域名。

何时使用

• 在调查需要使用 dnstwist 分析仿冒域名的安全事件时
• 在为该领域构建检测规则或威胁狩猎查询时
• 当 SOC 分析师需要针对此类分析的结构化流程时
• 在验证相关攻击技术的安全监控覆盖范围时

前置条件

• Python 3.9+ 并已安装 dnstwist（pip install dnstwist[full]）
• 可选：用于 IP 地理定位的 GeoIP 数据库
• 可选：用于数据增强的 Shodan API 密钥
• 执行 DNS 查询所需的网络访问
• 了解 DNS 记录类型和域名注册

关键概念

域名排列技术

DNSTwist 使用以下方式生成排列：添加（追加字符）、位翻转（位翻转错误）、同形字符（视觉相似的 Unicode 字符，如 rn 与 m）、连字符化（添加连字符）、插入（插入字符）、遗漏（删除字符）、重复（重复字符）、替换（替换为相邻键盘按键）、子域名（插入点）、转置（交换相邻字符）、元音交换（交换元音）以及基于字典（追加常见单词）。

模糊哈希与视觉相似度

DNSTwist 使用 ssdeep（局部敏感哈希）比较 HTML 内容，并使用 pHash（感知哈希）比较网页截图。这有助于识别在视觉上模仿合法网站的克隆钓鱼网站。较高的相似度分数表明很可能是钓鱼页面。

检测工作流

典型工作流为：生成域名排列 -> 解析 DNS 记录 -> 检查已注册域名 -> 比较网页相似度 -> 标记可疑域名 -> 通知安全团队 -> 请求下架。对于典型的企业域名，dnstwist 会生成 5,000-10,000 个排列。

工作流

步骤 1：基础域名排列扫描

import subprocess
import json
import csv
from datetime import datetime

def run_dnstwist_scan(domain, output_file=None):
    """Run dnstwist scan against a target domain."""
    cmd = [
        "dnstwist",
        "--registered",     # Only show registered domains
        "--format", "json", # Output in JSON
        "--nameservers", "8.8.8.8,1.1.1.1",
        "--threads", "50",
        "--mxcheck",        # Check MX records
        "--ssdeep",         # Fuzzy hash comparison
        "--geoip",          # GeoIP lookup
        domain,
    ]

    print(f"[*] Scanning permutations for: {domain}")
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=600)

    if result.returncode == 0:
        results = json.loads(result.stdout)
        registered = [r for r in results if r.get("dns_a") or r.get("dns_aaaa")]
        print(f"[+] Found {len(registered)} registered lookalike domains")

        if output_file:
            with open(output_file, "w") as f:
                json.dump(registered, f, indent=2)
            print(f"[+] Results saved to {output_file}")

        return registered
    else:
        print(f"[-] dnstwist error: {result.stderr}")
        return []

results = run_dnstwist_scan("example.com", "typosquat_results.json")

步骤 2：分析结果并确定优先级

def analyze_results(results, legitimate_ips=None):
    """Analyze dnstwist results and prioritize threats."""
    legitimate_ips = legitimate_ips or set()
    high_risk = []
    medium_risk = []
    low_risk = []

    for entry in results:
        domain = entry.get("domain", "")
        fuzzer = entry.get("fuzzer", "")
        dns_a = entry.get("dns_a", [])
        dns_mx = entry.get("dns_mx", [])
        ssdeep_score = entry.get("ssdeep_score", 0)

        risk_score = 0
        risk_factors = []

        # High similarity to legitimate site
        if ssdeep_score and ssdeep_score > 50:
            risk_score += 40
            risk_factors.append(f"high web similarity ({ssdeep_score}%)")

        # Has MX records (can receive email / phishing)
        if dns_mx:
            risk_score += 20
            risk_factors.append("has MX records (email capable)")

        # Recently registered (if whois data available)
        whois_created = entry.get("whois_created", "")
        if whois_created:
            try:
                created = datetime.fromisoformat(whois_created.replace("Z", "+00:00"))
                age_days = (datetime.now(created.tzinfo) - created).days
                if age_days < 30:
                    risk_score += 30
                    risk_factors.append(f"recently registered ({age_days} days)")
                elif age_days < 90:
                    risk_score += 15
                    risk_factors.append(f"registered {age_days} days ago")
            except (ValueError, TypeError):
                pass

        # Homoglyph attacks are highest risk
        if fuzzer == "homoglyph":
            risk_score += 25
            risk_factors.append("homoglyph (visually identical)")
        elif fuzzer in ("addition", "replacement", "transposition"):
            risk_score += 10
            risk_factors.append(f"permutation type: {fuzzer}")

        # Not pointing to legitimate infrastructure
        if dns_a and not set(dns_a).intersection(legitimate_ips):
            risk_score += 10
            risk_factors.append("different IP from legitimate")

        entry["risk_score"] = risk_score
        entry["risk_factors"] = risk_factors

        if risk_score >= 50:
            high_risk.append(entry)
        elif risk_score >= 25:
            medium_risk.append(entry)
        else:
            low_risk.append(entry)

    high_risk.sort(key=lambda x: x["risk_score"], reverse=True)
    medium_risk.sort(key=lambda x: x["risk_score"], reverse=True)

    print(f"\n=== Typosquatting Analysis ===")
    print(f"High Risk: {len(high_risk)}")
    print(f"Medium Risk: {len(medium_risk)}")
    print(f"Low Risk: {len(low_risk)}")

    if high_risk:
        print(f"\n--- High Risk Domains ---")
        for entry in high_risk[:10]:
            print(f"  {entry['domain']} (score: {entry['risk_score']})")
            for factor in entry['risk_factors']:
                print(f"    - {factor}")

    return {"high": high_risk, "medium": medium_risk, "low": low_risk}

analysis = analyze_results(results, legitimate_ips={"93.184.216.34"})

步骤 3：持续监控流水线

import time
import hashlib

class TyposquatMonitor:
    def __init__(self, domains, known_domains_file="known_typosquats.json"):
        self.domains = domains
        self.known_file = known_domains_file
        self.known_domains = self._load_known()

    def _load_known(self):
        try:
            with open(self.known_file, "r") as f:
                return json.load(f)
        except FileNotFoundError:
            return {}

    def _save_known(self):
        with open(self.known_file, "w") as f:
            json.dump(self.known_domains, f, indent=2)

    def scan_all_domains(self):
        """Scan all monitored domains for new typosquats."""
        new_findings = []
        for domain in self.domains:
            results = run_dnstwist_scan(domain)
            for entry in results:
                domain_key = entry.get("domain", "")
                if domain_key not in self.known_domains:
                    entry["first_seen"] = datetime.now().isoformat()
                    entry["monitored_domain"] = domain
                    self.known_domains[domain_key] = entry
                    new_findings.append(entry)
                    print(f"  [NEW] {domain_key} ({entry.get('fuzzer', '')})")

        self._save_known()
        print(f"\n[+] New typosquatting domains found: {len(new_findings)}")
        return new_findings

    def generate_alert(self, findings):
        """Generate alert for new high-risk typosquatting domains."""
        analysis = analyze_results(findings)
        alerts = []
        for entry in analysis["high"]:
            alerts.append({
                "severity": "HIGH",
                "domain": entry["domain"],
                "target": entry.get("monitored_domain", ""),
                "risk_score": entry["risk_score"],
                "risk_factors": entry["risk_factors"],
                "dns_a": entry.get("dns_a", []),
                "dns_mx": entry.get("dns_mx", []),
                "timestamp": datetime.now().isoformat(),
            })
        return alerts

monitor = TyposquatMonitor(["mycompany.com", "mycompany.org"])
new_findings = monitor.scan_all_domains()
alerts = monitor.generate_alert(new_findings)

步骤 4：导出用于阻止列表和下架

def export_blocklist(analysis, output_file="blocklist.txt"):
    """Export high-risk domains as blocklist for firewall/proxy."""
    domains = []
    for entry in analysis["high"] + analysis["medium"]:
        domain = entry.get("domain", "")
        if domain:
            domains.append(domain)

    with open(output_file, "w") as f:
        f.write(f"# Typosquatting blocklist generated {datetime.now().isoformat()}\n")
        for d in sorted(set(domains)):
            f.write(f"{d}\n")

    print(f"[+] Blocklist saved: {len(domains)} domains -> {output_file}")
    return domains

def generate_takedown_report(high_risk_domains):
    """Generate takedown request report."""
    report = f"""# Domain Takedown Request
Generated: {datetime.now().isoformat()}

## Summary
{len(high_risk_domains)} domains identified as potential typosquatting/phishing.

## Domains Requiring Takedown
"""
    for entry in high_risk_domains:
        report += f"""
### {entry['domain']}
- **Permutation Type**: {entry.get('fuzzer', 'unknown')}
- **IP Address**: {', '.join(entry.get('dns_a', ['N/A']))}
- **MX Records**: {', '.join(entry.get('dns_mx', ['N/A']))}
- **Risk Score**: {entry.get('risk_score', 0)}
- **Risk Factors**: {'; '.join(entry.get('risk_factors', []))}
- **Web Similarity**: {entry.get('ssdeep_score', 'N/A')}%
"""
    with open("takedown_report.md", "w") as f:
        f.write(report)
    print("[+] Takedown report generated: takedown_report.md")

export_blocklist(analysis)
generate_takedown_report(analysis["high"])

验证标准

• DNSTwist 为目标域名生成域名排列
• DNS 解析识别出已注册的相似域名
• 网页相似度评分检测出克隆钓鱼页面
• 风险评分按威胁等级对域名排序
• 持续监控检测出新注册的仿冒域名
• 阻止列表和下架报告正确生成

参考资料

• dnstwist GitHub 仓库
• dnstwister 在线服务
• HawkEye：使用 DNSTwist 检测仿冒域名
• Darktrace：监控仿冒域名
• Security Risk Advisors：域名监控
• Conscia：如何检测仿冒域名