CalvinBackup/www-project-ai-testing-guide
1
0
Fork 0
mirror of https://github.com/OWASP/www-project-ai-testing-guide.git synced 2026-03-22 18:23:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update AITG-APP-04_Testing_for_Input_Leakage.md

Browse Source
This commit is contained in:
Matteo Meucci
2025-11-13 20:22:25 +01:00
committed by GitHub
parent c317227cea
commit d0acf4a7c1
1 changed files with 4 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
Document/content/tests/AITG-APP-04_Testing_for_Input_Leakage.md
View File

@@ -1,4 +1,4 @@
## AITG-APP-04 - Testing for Input Leakage
# AITG-APP-04 - Testing for Input Leakage
### Summary
@@ -15,8 +15,6 @@ A lack of proof does not necessarily mean there is no leakage. Sensitive input c
Here's the reviewed and refined **Test/Payloads** section for **AITG-APP-04 - Testing for Input Leakage**, clearly specifying the responses indicating vulnerabilities:
---
### How to Test/Payloads
1. **Input Persistence Check**
@@ -145,18 +143,14 @@ A vulnerability is confirmed if the AI model:
- Deploy sensitive data guardrails capable of countering adversarial attempts to leak sensitive information.
- Ensure guardrails normalize inputs prior to filtering and detect obfuscated sensitive data and contextual cues in both inputs and outputs.
### Suggested Tools for this Specific Test
### Suggested Tools
- **Garak – Input Leakage Probe**: Specialized Garak module designed to detect sensitive input data leaks.
- **URL**: [https://github.com/NVIDIA/garak/blob/main/garak/probes/leakreveal.py](https://github.com/NVIDIA/garak/blob/main/garak/probes/leakreveal.py)
- **Microsoft Counterfit**: An AI security tool capable of testing for input leakage issues in model interactions.
- **URL**: [https://github.com/Azure/counterfit](https://github.com/Azure/counterfit)
### References
- **Title**: OWASP Top 10 LLM02:2025 Sensitive Information Disclosure
- **Author**: OWASP Foundation
- **Link**: [https://genai.owasp.org](https://genai.owasp.org)
- **Title**: NIST AI 100-2e2025 - Privacy Attacks and Mitigations
- **Author**: NIST
- **Link**: [https://doi.org/10.6028/NIST.AI.100-2e2025](https://doi.org/10.6028/NIST.AI.100-2e2025)
- OWASP Top 10 LLM02:2025 Sensitive Information Disclosure - [https://genai.owasp.org](https://genai.owasp.org/llmrisk/llm02-insecure-output-handling)
- NIST AI 100-2e2025 - Privacy Attacks and Mitigations - [https://doi.org/10.6028/NIST.AI.100-2e2025](https://doi.org/10.6028/NIST.AI.100-2e2025)