Before an LLM request leaves your app, inspect what it contains
说明与用途
Sether 用稳定的标记替换 LLM 提示中的敏感值,降低数据泄露风险,但并不保证完全合规。
问题
Sensitive data can leak from application to LLMs when requests are sent without proper redaction, risking privacy violations.
结果
Sether enables controlled redaction of sensitive data in LLM prompts, allowing developers to verify what data leaves the application and to restore tokens in responses, though it does not guarantee full compliance.
工作流
- 1. Create fictional messages with task instructions and sensitive values.
- 2. Run Sether to redact sensitive values, producing a tokenized prompt.
- 3. Inspect the redacted request, counting missed values and unnecessary replacements.
- 4. Send the redacted prompt to the LLM and evaluate task quality.
- 5. Receive the response, check for preserved tokens, and restore original values using the mapping.
- 6. Test edge cases: altered tokens, missing mappings, and streaming where values split across chunks.
证据
I am building Sether around that boundary. It is an open-source library that replaces detected sensitive values with stable tokens before text goes to an LLM.
The useful question is not “did we add a privacy tool?” It is “what actually left the application?”
A practical evaluation has four parts: ...
Streaming adds another case: a value may be split across chunks. Include that in your tests rather than relying only on complete strings.
Sether is not a promise that every sensitive value will be detected, and installing it does not establish regulatory compliance.
- 记录日期: 2026-10-02T08:41:01.635Z