CalvinBackup/www-project-ai-testing-guide
1
0
Fork 0
mirror of https://github.com/OWASP/www-project-ai-testing-guide.git synced 2026-06-01 03:51:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update AITG-INF-05_Testing_for_Fine-tuning_Poisoning.md

Browse Source
This commit is contained in:
Matteo Meucci
2025-11-13 19:57:18 +01:00
committed by GitHub
parent 90ef697a5a
commit c4c4e88137
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Document/content/tests/AITG-INF-05_Testing_for_Fine-tuning_Poisoning.md
+1 -1
View File
@@ -30,7 +30,7 @@ This test identifies vulnerabilities arising from poisoning during fine-tuning,
- **Activation-Based Monitoring and Pruning**: After fine-tuning, analyze the model's internal activations. Poisoned backdoors often create highly specific and unusual activation patterns. These can be detected and the corresponding neurons can be pruned to neutralize the backdoor.
- **Regular Red Teaming and Auditing**: Periodically conduct red teaming exercises where a dedicated team actively tries to poison the fine-tuning process. This helps uncover vulnerabilities in the MLOps pipeline before they can be exploited by real attackers.
### Suggested Tools for this Specific Test
### Suggested Tools
- **Adversarial Robustness Toolbox (ART)**
- Provides extensive tools for crafting poisoning attacks and implementing defenses, including data sanitization and activation-based detection.
- Tool Link: [ART on GitHub](https://github.com/Trusted-AI/adversarial-robustness-toolbox)