mirror of
https://github.com/Shiva108/ai-llm-red-team-handbook.git
synced 2026-08-27 21:30:27 +02:00
docs: Update banner image asset reference from banner.svg to page_header.svg across all documentation files.
This commit is contained in:
shiva108
+3
-3
@@ -79,10 +79,10 @@ The repository uses a dual-configuration strategy to support both legacy builds
|
||||
|
||||
#### Branding (Logo & Assets)
|
||||
|
||||
- **Asset Location**: `docs/assets/banner.svg`
|
||||
- **Asset Location**: `docs/assets/page_header.svg`
|
||||
- **Configuration**:
|
||||
- `.gitbook.yaml`: Defines `branding` block pointing to `docs/assets/banner.svg` (for new SaaS builds).
|
||||
- `book.json`: Defines `insert-logo` plugin pointing to `assets/banner.svg` (relative to `docs` root).
|
||||
- `.gitbook.yaml`: Defines `branding` block pointing to `docs/assets/page_header.svg` (for new SaaS builds).
|
||||
- `book.json`: Defines `insert-logo` plugin pointing to `assets/page_header.svg` (relative to `docs` root).
|
||||
- **Note**: GitBook Cloud (SaaS) often ignores file-based theming. If the logo does not appear, you must set it manually via **Customize > Look & Feel** in the GitBook Dashboard.
|
||||
|
||||
#### Plugins (Legacy)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Red Teaming AI & LLMs: The Consultant’s Complete Handbook
|
||||
|
||||
|
||||
|
||||
|
||||
## Table of Contents
|
||||
|
||||
@@ -104,7 +104,7 @@ _(To be added)_
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 1: Introduction to AI Red Teaming
|
||||
|
||||
@@ -187,7 +187,7 @@ The handbook is organized for practical learning and use:
|
||||
|
||||
_Proceed to the next chapter to explore ethical and legal essentials, and begin developing the professional approach required of every AI red teamer._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 2: Ethics, Legal, and Stakeholder Communication
|
||||
|
||||
@@ -289,7 +289,7 @@ In AI red teaming, technical findings may have legal, business, or even social i
|
||||
|
||||
_In the next chapter, you’ll develop the mindset that distinguishes effective AI red teamers from traditional security testers, bridging technology, psychology, and business acuity._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 3: The Red Teamer's Mindset
|
||||
|
||||
@@ -369,7 +369,7 @@ Field engagements can be high-stress: production outages, tense clients, critica
|
||||
|
||||
_Mastering the red team mindset primes you for the work ahead: scoping, planning, and then executing engagements with insight, rigor, and integrity. Proceed to the next chapter to learn how to prepare and manage a professional AI red team project from start to finish._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 4: SOW, Rules of Engagement, and Client Onboarding
|
||||
|
||||
@@ -488,7 +488,7 @@ Before you start:
|
||||
|
||||
_Solid foundations prevent project failure and foster trust. The next chapter will guide you through threat modeling and risk analysis for AI systems, helping you identify what matters most before you begin attacking._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 5: Threat Modeling and Risk Analysis
|
||||
|
||||
@@ -613,7 +613,7 @@ A good threat model is:
|
||||
|
||||
_With a strong threat model, your red team engagement becomes risk-driven and results-focused. The next chapter will walk you through scoping these findings into a feasible, valuable engagement plan._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 6: Scoping an Engagement
|
||||
|
||||
@@ -721,7 +721,7 @@ An accurately scoped engagement shows professionalism and respect for the client
|
||||
|
||||
_With a precise scope in place, you are ready to establish the laboratory, test environments, and safety measures needed for executing a secure and efficient AI red teaming exercise. Continue to the next chapter for practical lab setup and environmental safety._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 7: Lab Setup and Environmental Safety
|
||||
|
||||
@@ -816,7 +816,7 @@ Remember:
|
||||
|
||||
_With a robust lab and clear safety controls in place, you’re prepared to gather and preserve evidence in a trustworthy manner. Continue to the next chapter to master documentation and evidence handling in AI red team engagements._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 8: Evidence, Documentation, and Chain of Custody
|
||||
|
||||
@@ -930,9 +930,9 @@ A robust chain of custody ensures that all evidence remains trustworthy and trac
|
||||
|
||||
_With evidence and documentation in place, you’re equipped to deliver clear, credible findings. The next chapter will guide you through the art of writing actionable, impactful red team reports for both technical and executive audiences._
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 9: LLM Architectures and System Components
|
||||
|
||||
@@ -1071,11 +1071,11 @@ Before attacking, answer these questions about your target:
|
||||
|
||||
Understanding these components transitions you from "guessing passwords" to "engineering exploits."
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 10: Tokenization, Context, and Generation
|
||||
|
||||
|
||||
|
||||
|
||||
While the "mind" of an LLM is a neural network, its "senses" are defined by the Tokenizer, and its "memory" is defined by the Context Window. As a Red Teamer, deeply understanding these mechanisms allows you to exploit blind spots, bypass filters, and degrade model performance.
|
||||
|
||||
@@ -1288,7 +1288,7 @@ Understanding plugins is critical because they turn a "text generator" into an "
|
||||
|
||||
# Chapter 12: Retrieval-Augmented Generation (RAG) Pipelines
|
||||
|
||||
|
||||
|
||||
|
||||
## 12.1 What Is Retrieval-Augmented Generation (RAG)?
|
||||
|
||||
@@ -3815,7 +3815,7 @@ class RAGAccessControlTester:
|
||||
|
||||
_RAG systems represent one of the most powerful - and vulnerable - implementations of LLM technology in enterprise environments. By understanding their architecture, attack surfaces, and testing methodologies, red teamers can help organizations build secure, production-ready AI assistants. The next chapter will explore data provenance and supply chain security - critical for understanding where your AI system's data comes from and how it can be compromised._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 13: Data Provenance and Supply Chain Security
|
||||
|
||||
@@ -5676,7 +5676,7 @@ def detect_insider_poisoning(training_data, baseline_distribution):
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 14: Prompt Injection (Direct/Indirect, 1st/3rd Party)
|
||||
|
||||
@@ -9746,7 +9746,7 @@ _Prompt injection represents the defining security challenge of the LLM era. Lik
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 15: Data Leakage and Extraction
|
||||
|
||||
@@ -13416,7 +13416,7 @@ _Continue to Chapter 16: Jailbreaks and Bypass Techniques to learn how attackers
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 16: Jailbreaks and Bypass Techniques
|
||||
|
||||
@@ -14962,7 +14962,7 @@ Successful reports are tailored to multiple audiences, such as:
|
||||
|
||||
_You are now ready to communicate your findings with clarity and impact. The next chapter will cover presenting results to both technical and non-technical stakeholders - ensuring your work leads to measurable improvements in AI security._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 37: Presenting Results and Remediation Guidance
|
||||
|
||||
@@ -15048,7 +15048,7 @@ Delivering findings is more than handing over a report - it's about ensuring you
|
||||
|
||||
_Professional communication and practical remediation guidance ensure your red teaming work translates into real, measurable improvements. The next chapter will explore lessons learned, common pitfalls, and how to build a mature AI/LLM red teaming practice._
|
||||
|
||||
|
||||
|
||||
|
||||
# Chapter 38: Lessons Learned and Building Future Readiness
|
||||
|
||||
@@ -15108,4 +15108,4 @@ To make AI red teaming a sustainable part of your organization’s security post
|
||||
|
||||
_By systematically learning and adapting, your AI red teaming program matures - helping organizations stay resilient amid the evolving risks and rewards of intelligent systems._
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# **AI/LLM Red Team Field Manual**
|
||||
|
||||
@@ -186,7 +186,7 @@ For step-by-step attack procedures with extensive code examples, see the **modul
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **1. Introduction: Rules of Engagement (RoE)**
|
||||
|
||||
@@ -204,7 +204,7 @@ Define in writing: in-scope systems/models, allowed techniques, test windows, ha
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **1.5 Environment Setup & Configuration**
|
||||
|
||||
@@ -490,7 +490,7 @@ API Config File: ✅
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **2. Red Teaming Phases**
|
||||
|
||||
@@ -765,7 +765,7 @@ chmod +x cleanup.sh
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **3\. Attack Types & Practical Test Examples**
|
||||
|
||||
@@ -1250,7 +1250,7 @@ afl-fuzz \-i testcase_dir \-o findings_dir \-- ./your_cli_target @@
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **4\. Tools Reference & CLI Commands**
|
||||
|
||||
@@ -1296,7 +1296,7 @@ afl-fuzz \-i testcase_dir \-o findings_dir \-- ./your_cli_target @@
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **5\. Attack-Type–to–Tool Quick Lookup Table**
|
||||
|
||||
@@ -1315,7 +1315,7 @@ afl-fuzz \-i testcase_dir \-o findings_dir \-- ./your_cli_target @@
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **5.5 API Configuration Guide**
|
||||
|
||||
@@ -1583,7 +1583,7 @@ echo "✅ Provider test complete!"
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **6\. Reporting Guidance**
|
||||
|
||||
@@ -1597,7 +1597,7 @@ Report every finding with:
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **7\. Additional Guidance**
|
||||
|
||||
@@ -1609,7 +1609,7 @@ Report every finding with:
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
## **8. Troubleshooting Guide**
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 1: Introduction to AI Red Teaming
|
||||
|
||||
|
||||
|
||||
|
||||
## 1.1 What Is AI Red Teaming?
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 2: Ethics, Legal, and Stakeholder Communication
|
||||
|
||||
S
|
||||
S
|
||||
|
||||
## 2.1 Why Ethics Matter in AI Red Teaming
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 3: The Red Teamer's Mindset
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 4: SOW, Rules of Engagement, and Client Onboarding
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 5: Threat Modeling and Risk Analysis
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 6: Scoping an Engagement
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 7: Lab Setup and Environmental Safety
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 8: Evidence, Documentation, and Chain of Custody
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 9: LLM Architectures and System Components
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 10: Tokenization, Context, and Generation
|
||||
|
||||
|
||||
|
||||
|
||||
While the "mind" of an LLM is a neural network, its "senses" are defined by the Tokenizer, and its "memory" is defined by the Context Window. As a Red Teamer, deeply understanding these mechanisms allows you to exploit blind spots, bypass filters, and degrade model performance.
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 11: Plugins, Extensions, and External APIs
|
||||
|
||||
|
||||
|
||||
|
||||
Modern LLMs are no longer isolated "chatbots." Through plugins, functions, and extensions, they can browse the web, read emails, query databases, and execute code. This capability introduces the **Tool-Use Attack Surface**, where the LLM becomes a "privileged user" that attackers can manipulate.
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 12: Retrieval-Augmented Generation (RAG) Pipelines
|
||||
|
||||
|
||||
|
||||
|
||||
## 12.1 What Is Retrieval-Augmented Generation (RAG)?
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 13: Data Provenance and Supply Chain Security
|
||||
|
||||
|
||||
|
||||
|
||||
## 13.1 Understanding Data Provenance in AI/LLM Systems
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 14: Prompt Injection (Direct/Indirect, 1st/3rd Party)
|
||||
|
||||
|
||||
|
||||
|
||||
## 14.1 Introduction to Prompt Injection
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 15: Data Leakage and Extraction
|
||||
|
||||
|
||||
|
||||
|
||||
## 15.1 Introduction to Data Leakage in LLMs
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 16: Jailbreaks and Bypass Techniques
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 17: Plugin and API Exploitation
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 18: Evasion, Obfuscation, and Adversarial Inputs
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 19: Training Data Poisoning
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 20: Model Theft and Membership Inference
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 21: Model DoS and Resource Exhaustion
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 22: Cross-Modal and Multimodal Attacks
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 23: Advanced Persistence and Chaining
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 24: Social Engineering with LLM
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 25: Advanced Adversarial ML
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 26: Supply Chain Attacks on AI
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 27: Federated Learning Attacks
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 28: AI Privacy Attacks
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 29: Model Inversion Attacks
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 30: Backdoor Attacks
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 31: AI System Reconnaissance
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 32: Automated Attack Frameworks
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 33: Red Team Automation
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 34: Defense Evasion Techniques
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 35: Post-Exploitation in AI Systems
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 36: Reporting and Communication
|
||||
|
||||
|
||||
|
||||
|
||||
## 36.1 The Purpose of Red Team Reports
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 37: Remediation Strategies
|
||||
|
||||
|
||||
|
||||
|
||||
## 37.1 The Importance of Presentation
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 38: Continuous Red Teaming
|
||||
|
||||
|
||||
|
||||
|
||||
## 38.1 Common Pitfalls in AI/LLM Red Teaming
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 39: AI Bug Bounty Programs
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 40: Compliance and Standards
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 41: Industry Best Practices
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 42: Case Studies and War Stories
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 43: Future of AI Red Teaming
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 44: Emerging Threats
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Chapter 45: Building an AI Red Team Program
|
||||
|
||||
|
||||
|
||||
|
||||
## 1.0 Introduction: The Imperative for AI-Specific Red Teaming
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Chapter 46: Conclusion and Next Steps
|
||||
|
||||
|
||||
+1
-1
@@ -2,7 +2,7 @@
|
||||
|
||||
Version 0.024.63
|
||||
|
||||
|
||||
|
||||
|
||||
## Introduction
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 01: Prompt Injection
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 02: Data Leakage & Extraction
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 03: Jailbreaks & Bypass
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 04: Plugin & API Exploitation
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 05: Evasion & Obfuscation
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 06: Data Poisoning
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 07: Model Theft & Extraction
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 08: DoS & Resource Exhaustion
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 09: Multimodal Attacks
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 10: Persistence & Chaining
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual Playbook 11: Social Engineering with LLMs
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
|
||||
|
||||
|
||||
# Field Manual - Quick Reference Card
|
||||
|
||||
|
||||
Reference in New Issue
Block a user