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

Merge pull request #56 from mmorana1/patch-23

Browse Source 
Update 2.1.2_Identify_RAI_threats.md
This commit is contained in:
Matteo Meucci
2025-11-17 18:48:30 +01:00
committed by GitHub
parent bce5e85aa0 9c5af76f6f
commit 1a25dfee30
1 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Document/content/2.1.2_Identify_RAI_threats.md
+13 -13
View File
@@ -16,7 +16,7 @@ Before we review it, let's briefly revisit key Trustworthy AI concepts defined b
Based on these concepts, we carefully revise your previous identification of threats:
<p align="center">
<img src="/Document/images/RT-Threats.png" alt="RAI Threat Model" width="1200"/>
<img src="/Document/images/TAI Threats SAIF Mapping.png" alt="RAI Threat Model" width="1200"/>
</p>
*Fig. 3 Responsible AI Threat modeling*
@@ -25,27 +25,27 @@ Based on these concepts, we carefully revise your previous identification of thr
#### **🟦 AI Application (4 additions):**
1. Hallucinations
2. Toxic Content Generation
3. Automation Bias
4. Lack of Explainability
5. Lack of Accountability in Agent/Plugin Actions
1. Hallucinations (T01-HAL)
2. Toxic Content Generation (T01-TCG)
3. Automation Bias (T01-AB)
4. Lack of Explainability (T01-LoE)
5. Lack of Accountability in Agent/Plugin Actions (T01-LoA)
#### **🟪 AI Model (3 additions):**
6. Bias and Discrimination
7. Overfitting and Generalization
8. Misalignment with Human Intent
6. Bias and Discrimination (T01-B&D)
7. Overfitting and Generalization (T01-O&B)
8. Misalignment with Human Intent (T01-MHI)
#### **🟩 AI Infrastructure (2 additions):**
9. Lack of Traceability & Auditability of Infrastructure Processes
9. Lack of Traceability (T01-LoT) & Lack of Auditability (T01-LoA) of Infrastructure Processes
#### **🟨 AI Data (3 additions):**
10. Non-representative Training Data
11. Toxic or Harmful Training Data
12. Data Privacy Violations
10. Non-representative Training Data (T01-NRTD)
11. Toxic or Harmful Training Data (T01-T&HD)
12. Data Privacy Violations (T01-DPV)
The following tables provide a structured overview, facilitating clear visibility for identifying, managing, and mitigating critical Responsible AI and Trustworthy AI (RT) threats across your entire AI system architecture.