- Removed the inline Mermaid diagram definition for the secure document ingestion pipeline.
- Replaced the diagram with a reference to a pre-rendered image (assets/rec21_secure_ingestion.png).
- Ensures consistent visual representation of the pipeline across different markdown viewers.
- Avoids potential rendering issues or inconsistencies associated with dynamic Mermaid diagrams.
- Add a new schematic image to visually represent the supply chain components.
- Resize the 'Model Poisoning Flow' image for improved layout and readability.
- Enhance the visual clarity of the 'Data Provenance and Supply Chain Security' chapter.
- remove outdated supply chain map image
- replace model poisoning flow image with a clearer version
- update image width for improved readability
- enhance visual explanations within the chapter
- Convert the secure ingestion flow diagram from a simple list to a mermaid graph TD flowchart.
- Enhance visual clarity and structure of the secure ingestion process.
- Explicitly show rejection paths for malware scans and format validation.
- Improve readability and understanding of the RAG pipeline's secure ingestion steps.
- Add detailed network isolation methods using Docker, VMs, and iptables for secure lab environments.
- Introduce multiple LLM setup options including Ollama, Text-Generation-WebUI, and llama.cpp for diverse testing needs.
- Integrate practical red teaming tools like Garak and a core Python environment for automated vulnerability scanning.
- Implement robust environmental safety mechanisms: a comprehensive kill switch, watchdog timer, API rate limiter, and cost tracker.
- Update .gitignore to exclude old_chapter_07.md, cleaning up old file references.
- Add a visual flowchart for the safety watchdog script.
- Enhance understanding of the autonomous agent kill switch implementation.
- Illustrates the monitoring and termination logic for exceeding thresholds.
- Refresh model pricing for OpenAI, Anthropic, and Google APIs.
- Update tool installation instructions and notes for vLLM and llama.cpp.
- Change default Anthropic model to claude-3-5-haiku-latest.
- Add advisories to verify external tool versions and API pricing due to rapid evolution.
- Remove deprecated version: "3.8" from Docker Compose examples for clarity.
- Reworded numerous sections and paragraphs for improved clarity and conciseness.
- Simplified sentence structures and adopted a more direct, imperative tone throughout the chapter.
- Shortened section titles and bullet points to enhance readability and reduce verbosity.
- Updated .gitignore to exclude final_audit.json, a new output file from lab processes.
- Aims to make the technical guidance more accessible and easier to digest for readers.
- Added detailed decision guides for local LLM deployment options and virtualization.
- Enhanced guidance for commercial LLM API testing, including cost, rate limiting, and logging.
- Provided a comprehensive overview of network isolation strategies and their GPU support.
- Introduced essential red team tooling categories and explained the use of Garak.
- Detailed the importance of kill switches, watchdog timers, and rate limiters for lab safety.
- Embed three new diagrams in Chapter 7 documentation.
- Provide visual explanations for proxy traffic interception.
- Illustrate the architectural setup for Docker-based lab isolation.
- Detail the execution flow of the custom test harness.
- Enhance readability and comprehension of complex lab setup procedures.
- Significantly expanded Chapter 7 with detailed guides and code examples for AI red teaming lab setup.
- Introduced comprehensive sections on local LLM deployment, API-based testing, and network isolation.
- Added critical safety controls including kill switches, watchdog timers, rate limiting, and cost management.
- Included advanced topics such as testing RAG, agent systems, and multi-modal models.
- Provided pre-engagement and daily operational checklists, risk management, and incident response procedures.
- Convert all prompt and attack examples from plain text to YAML format.
- Enhance the readability and structure of complex jailbreak techniques.
- Provide clearer delineation of different parts within multi-step prompts.
- Implement URL scheme validation for LLM endpoint connections.
- Mitigate Server-Side Request Forgery (SSRF) by ensuring only 'http' and 'https' schemes are allowed.
- Sanitize report output paths to prevent directory traversal attacks.
- Ensure test reports are saved only within the current working directory.
- Update RAG pipeline documentation to use Mermaid for improved flow diagram rendering.
- Converted generic text code blocks to specific formats like yaml, bash, math, and python.
- Improves syntax highlighting and semantic understanding of examples.
- Replaced several text blocks with Markdown tables for enhanced readability.
- Provides a clearer, more structured presentation for key concepts.
- Removed redundant horizontal rules at the end of the chapter.
- Reformat various attack examples and flows into more structured tables or code blocks.
- Convert plain text and generic YAML blocks to specific python, markdown, or yaml code fences.
- Update table headers and content for enhanced clarity and consistency across the document.
- Standardize the presentation of attack methodologies and vulnerability scan results.
- Enhance overall documentation readability for complex security concepts.
- Converted various plain text and code block examples into structured Markdown tables or YAML.
- Improved readability and clarity of complex attack scenarios and processes.
- Enhanced the visual presentation of security concepts within the chapter.
- Applied to examples including model naming, backdoor triggers, data poisoning, and supply chain attacks.
- Restructure the Content field in the RAG pipeline example.
- Convert the content from a single multi-line string to a list of items.
- Explicitly define question/answer pairs and system instruction injections.
- Improve the clarity and readability of the YAML example for RAG content.
- The example malicious document in the RAG pipelines chapter was updated.
- Changed the code block from markdown to YAML syntax.
- This provides a more structured representation of the document content.
- Improves clarity and consistency of the example's presentation.
- Converted the "Example Attack" section for metadata leakage from a text block to a Markdown table.
- This change enhances readability and provides a clearer, more structured presentation of the information.
- Delineates leakage types and the specific information revealed during a metadata attack.
- Converted RAG query examples from plain text to a Markdown table.
- Updated the example Trojan Document to use a YAML code block.
- Enhanced the readability and structure of code examples within the RAG chapter.
- Convert attack flow and scenario steps into structured Markdown tables.
- Enhance readability for complex sequences like chunk reconstruction and provenance attacks.
- Update the restricted user query example to use YAML block for better representation of multi-line responses.
- Improve overall presentation and clarity of examples within the RAG Pipelines chapter.
- Converted a plain text example block to YAML format.
- Enhances clarity and structure for the RAG pipeline attack scenario.
- Improves consistency in documentation examples.
- Reformat test cases for Retrieval Augmented Generation (RAG) pipeline vulnerabilities.
- Present test scenarios, inputs, expected behaviors, and vulnerability indicators in a clear Markdown table.
- Enhance readability and consistency of the documentation for security test cases.
- Converted the "Attacker Query Sequence" example from plain text to a Markdown table.
- Improves readability and structure of the example content.
- Enhances presentation for better understanding of the query steps and outcomes.
shiva108