How Does PII Detection Work?
PII detection identifies personal data in text using pattern matching and machine learning. anonym.legal uses a hybrid approach:
- 1Pattern Matching: Regex patterns detect structured data (SSNs, credit cards, IBANs) with checksum validation.
- 2Named Entity Recognition: NER models identify names, locations, and organizations in 48 languages.
- 3Context Scoring: Each detection is scored based on surrounding context to minimize false positives.
This hybrid approach detects 285+ entity types while maintaining deterministic, reproducible results — essential for compliance and legal discovery.
为什么选择正则表达式，而不是AI？
我们的方式
- 100%可重复的结果
- 完全可审计以确保合规性
- 不需要训练数据
- 透明的决策过程
- 快速、可预测的性能
- 没有模型漂移
AI/ML方法
- 结果在不同运行之间变化
- 黑箱决策过程
- 需要训练数据
- 难以审计
- 更高的计算成本
- 模型漂移
10步流程
从输入到输出，您的文档到底发生了什么
输入文本
通过Web界面、API或Office插件提交您的文档
语言检测
系统识别文档语言以进行最佳处理
标记化
文本被分解为标记以进行模式匹配
模式匹配
正则表达式模式扫描50多种实体类型
上下文分析
周围文本提高检测准确性
置信度评分
每个检测都会获得一个置信度评分
实体分类
检测到的项目按类型分类
查看结果
查看所有检测结果及其位置和评分
应用匿名化
选择您的方法：替换、编辑、哈希、加密或掩码
输出文档
下载您的匿名化文档
MCP服务器：隐私优先的AI集成
您的数据如何通过MCP服务器流动以保持AI工具的安全
AI工具请求
您的AI工具（Cursor，Claude）发送包含PII的请求
MCP服务器拦截
服务器分析并检测所有PII实体
匿名化
PII被替换为令牌或编辑
AI处理
AI仅接收和处理匿名化数据
响应返回
AI响应通过MCP服务器返回
去令牌化
可选：为用户恢复原始值
真实世界示例
为John Doe处理付款，电子邮件john@example.com，卡号4532-1111-2222-3333AI看到的内容
为PII_PERSON_001处理付款，电子邮件PII_EMAIL_001，卡号PII_CREDIT_CARD_001您收到的内容
Frequently Asked Questions
Why use regex instead of AI for PII detection?
Regex-based detection is deterministic and reproducible. The same input always produces the same output. AI/ML models can be unpredictable and may miss or falsely flag data. For compliance, reproducibility matters.
How accurate is the detection?
Our hybrid approach combines regex patterns with Named Entity Recognition (NER) for high accuracy. All patterns include checksum validation where applicable (credit cards, IBANs, SSNs). False positives are minimized through context-aware scoring.
What happens to my data during processing?
Text is sent to our EU-hosted servers (Hetzner, Germany) over TLS 1.3 for analysis. We don't store your data after processing. With Zero-Knowledge auth, we can't even identify which user made the request.
Can I add custom entity types?
Yes! You can create custom recognizers with your own regex patterns and context words. Custom entities support the same operators (replace, mask, hash, encrypt, redact) as built-in types.
How does reversible encryption work?
The Encrypt operator uses AES-256-GCM encryption with your key. Only you can decrypt. This allows re-identification for audits or legal discovery while keeping data protected in transit and storage.