CalvinBackup/ai-llm-red-team-handbook
1
0 Fork 0
mirror of https://github.com/Shiva108/ai-llm-red-team-handbook.git synced 2026-10-13 19:21:05 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: adjust markdown code block fences and minor text formatting

Browse Source
This commit is contained in:
shiva108 committed 2025-12-06 10:50:52 +01:00
1 parent c50979a222
commit 198cfb240c
3 files changed
+32 -32
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/AI LLM Red Team Handbook.md
+26 -25
View File
@@ -269,11 +269,11 @@ In AI red teaming, technical findings may have legal, business, or even social i
### Example: Reporting Table
| Audience | Communication Style | Example Message |
| ---------------- | --------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
| Executive | Plain language, impact-focused | “Our tests found that anyone can access sensitive customer data in the chat logs, exposing us to GDPR fines.” |
| Audience | Communication Style | Example Message |
| ---------------- | --------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| Executive | Plain language, impact-focused | “Our tests found that anyone can access sensitive customer data in the chat logs, exposing us to GDPR fines.” |
| Technical | Technical detail, steps, evidence | “Prompt injection via the ‘/support’ API bypasses intent filters - recommend input validation and stricter role separation.” |
| Compliance/Legal | Documentation, traceability | “All model access was conducted using the provided test account and logs are attached as evidence.” |
| Compliance/Legal | Documentation, traceability | “All model access was conducted using the provided test account and logs are attached as evidence.” |
## 2.6 Conflicts of Interest, Bias, and Fair Testing
@@ -12306,27 +12306,28 @@ Priority actions based on severity:
# Example: Testing memorization on different models
MEMORIZATION_BENCHMARK = {
'model': 'GPT-2-1.5B',
'training_set_size': '40GB',
'test_samples': 1000,
'extraction_techniques': [
'Direct completion',
'Prefix-suffix attack',
'Temperature manipulation'
],
'results': {
'exact_matches': 127, # 12.7%
'near_matches': 234, # 23.4%
'partial_matches': 445, # 44.5%
'no_match': 194 # 19.4%
},
'success_factors': [
'Unique sequences: 85% extraction rate',
'Common sequences: 15% extraction rate',
'Repeated data: 95% extraction rate'
]
'model': 'GPT-2-1.5B',
'training_set_size': '40GB',
'test_samples': 1000,
'extraction_techniques': [
'Direct completion',
'Prefix-suffix attack',
'Temperature manipulation'
],
'results': {
'exact_matches': 127, # 12.7%
'near_matches': 234, # 23.4%
'partial_matches': 445, # 44.5%
'no_match': 194 # 19.4%
},
'success_factors': [
'Unique sequences: 85% extraction rate',
'Common sequences: 15% extraction rate',
'Repeated data: 95% extraction rate'
]
}
```
````
**Success rates and methodologies**
@@ -12403,7 +12404,7 @@ MEMORIZATION_BENCHMARK = {
3. Update controls based on new threats
4. Regular penetration testing
5. Continuous improvement
```
````
---
docs/Chapter_02_Ethics_Legal_and_Stakeholder_Communication.md
+6 -6
View File
@@ -1,7 +1,7 @@
![Banner](assets/banner.svg)
# Chapter 2: Ethics, Legal, and Stakeholder Communication
![Banner](assets/banner.svg)S
## 2.1 Why Ethics Matter in AI Red Teaming
AI red teaming, by its very nature, grants you deep access to sensitive systems and data. With that access comes the responsibility to operate with integrity, professionalism, and a commitment to avoiding harm. Ethical lapses don’t just damage your reputation - they can put clients, end users, and even whole organizations at risk.
@@ -80,11 +80,11 @@ In AI red teaming, technical findings may have legal, business, or even social i
### Example: Reporting Table
| Audience | Communication Style | Example Message |
| ---------------- | --------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
| Executive | Plain language, impact-focused | “Our tests found that anyone can access sensitive customer data in the chat logs, exposing us to GDPR fines.” |
| Audience | Communication Style | Example Message |
| ---------------- | --------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| Executive | Plain language, impact-focused | “Our tests found that anyone can access sensitive customer data in the chat logs, exposing us to GDPR fines.” |
| Technical | Technical detail, steps, evidence | “Prompt injection via the ‘/support’ API bypasses intent filters - recommend input validation and stricter role separation.” |
| Compliance/Legal | Documentation, traceability | “All model access was conducted using the provided test account and logs are attached as evidence.” |
| Compliance/Legal | Documentation, traceability | “All model access was conducted using the provided test account and logs are attached as evidence.” |
## 2.6 Conflicts of Interest, Bias, and Fair Testing
docs/Chapter_16_Jailbreaks_and_Bypass_Techniques.md
-1
View File
@@ -1419,4 +1419,3 @@ RED_TEAM_BEST_PRACTICES = {
**Key Takeaway**: Jailbreak research is essential for AI safety. Responsible testing, coordinated disclosure, and continuous improvement are critical for building robust, trustworthy AI systems.
---