The non-obvious takeaway is that de-identification works as a governance problem as much as a technical one: protection only holds if every pipeline runs the current version and compliant config, so Airbnb folded it into the shared workflow and model registry. Engineering teams handling user text for training can reuse the pattern of deterministic per-run faker replacement plus GLiNER for street addresses. Teams in ASEAN and China dealing with multi-language support data can note that metrics are tracked per language, with conservative fallbacks when language detection is unstable.
#data masking
5 stories · 1 in 7 days · 1 in 30 days
Stories, products and papers tagged "data masking", newest first.
Nov 18
Airbnb uses Presidio to de-identify training text with fake data
Sep 30
Aug 10
Chinese contentLangSmith LLM Gateway 新增数据保护:检测并编辑 PII 与密钥
LangChain 给 LangSmith 网关加了数据保护,请求发出前自动识别并替换 PII 和密钥,企业用户可申请测试。
Jul 31
Chinese contentLangSmith Gateway 公开测试版发布,集成编程代理与成本控制
LangChain 发了新网关,能控制花销和速率,还能自动给数据脱敏,跟编程代理直接连,甚至支持 kimi-k3,干活更方便了。
May 29
Chinese contentLangSmith LLM Gateway 可自动脱敏请求中的敏感数据
做 AI 应用开发的团队终于有了一个简单有效的数据脱敏方案,尤其是处理用户隐私数据的场景,建议直接集成到你的 LLM 调用流程中。