CalvinBackup/ai-llm-red-team-handbook
1
0 Fork 0
mirror of https://github.com/Shiva108/ai-llm-red-team-handbook.git synced 2026-10-14 03:31:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

More centering

Browse Source
This commit is contained in:
shiva108 committed 2026-01-10 10:45:58 +01:00
1 parent edefb64b2e
commit bf480c23c6
23 files changed
+222 -68
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/Chapter_09_LLM_Architectures_and_System_Components.md
+12 -4
View File
@@ -11,7 +11,9 @@ Related: Chapters 10 (Tokenization), 11 (Plugins), 12 (RAG)
# Chapter 9: LLM Architectures and System Components
![ ](assets/page_header.svg)
<p align="center">
<img src="assets/page_header.svg" alt="Chapter 9 Header">
</p>
_This chapter provides deep technical understanding of LLM architectures critical for red teaming. You'll learn transformer internals, attention mechanisms, embedding spaces, system prompts and context windows, model deployment patterns, and how architectural choices create specific attack surfaces that red teamers can exploit._
@@ -30,7 +32,9 @@ When we attack an "AI," we are rarely attacking a single file. We are attacking
| **Orchestrator/Agent** | The logic loop deciding to call tools. | Infinite loops, excessive agency, prompt injection propagation. |
| **Vector Database (RAG)** | Long-term memory storage. | Search result poisoning, indirect prompt injection. |
<img src="assets/chapter_09_rec_14_compound_ai.png" alt="Compound AI System" width="768">
<p align="center">
<img src="assets/chapter_09_rec_14_compound_ai.png" alt="Compound AI System" width="768">
</p>
## 9.2 The Transformer: A Hacker's Perspective
@@ -99,9 +103,13 @@ Understanding the flow of a single prompt helps you pinpoint where to inject.
3. **Output Post-processing**:
- _Attack:_ **Obfuscation**. If the output filter catches "bomb", generating "b-o-m-b" might bypass it.
<img src="assets/rec10_inference_pipeline.svg" alt="Inference Pipeline Diagram" width="768">
<p align="center">
<img src="assets/rec10_inference_pipeline.svg" alt="Inference Pipeline Diagram" width="768">
</p>
<img src="assets/chapter_09_rec_15_inference_pipeline.png" alt="Inference Pipeline Diagram" width="768">
<p align="center">
<img src="assets/chapter_09_rec_15_inference_pipeline.png" alt="Inference Pipeline Diagram" width="768">
</p>
## 9.5 Practical Inspection: Loading a Model