Commit Graph

240 Commits

Author SHA1 Message Date
shiva108 b1462b5df3 docs: Remove Part III: Operational Workflows and its associated chapters. 2025-12-05 18:44:17 +01:00
shiva108 c8add7c6b2 docs: Reorganize chapter structure and update part headings in SUMMARY.md, and adjust banner position in Chapter 11. 2025-12-05 18:43:13 +01:00
shiva108 c24d47f6eb refactor: Reorganize handbook chapters, moving reporting and remediation content to later sections and introducing new LLM technical topics. 2025-12-05 18:42:18 +01:00
shiva108 24135fda51 refactor: Consolidate AI Red Team building content, update the handbook's summary, and adjust the banner placement. 2025-12-05 18:37:57 +01:00
shiva108 f7db15d26c docs: Overhaul AI LLM Red Team Handbook table of contents, introducing linked chapters, new parts, and field manuals. 2025-12-05 18:34:57 +01:00
shiva108 fd8a42b8eb docs: add version number to summary 2025-12-05 18:30:38 +01:00
shiva108 00f37cfa65 feat: update book version and summary structure, and remove comscore theme plugin. 2025-12-05 18:29:56 +01:00
shiva108 d6fb52c02e docs: Add an introduction and update part numbering in SUMMARY.md 2025-12-05 18:26:36 +01:00
shiva108 eb21b9b95d feat: Add banner image to all documentation chapters and field manuals. 2025-12-05 18:13:16 +01:00
shiva108 ee7032b623 chore: delete placeholder chapter creation script and update SUMMARY.md introduction to a todo. 2025-12-05 13:27:38 +01:00
shiva108 a00329ae8f feat: Add detailed attack playbook section with links and usage guidance, and apply minor formatting adjustments. 2025-12-05 13:18:12 +01:00
shiva108 fa54aa3b00 feat: Add new field manual playbooks for various attack types, quick reference, and index, updating the summary. 2025-12-05 12:18:00 +01:00
shiva108 419099c8ac feat: Add placeholder chapters 25-46, book configuration files, a creation script, and update the summary. 2025-12-05 10:41:12 +01:00
shiva108 5a034972e3 docs: remove placeholder "chapter continues" notes from chapter endings 2025-12-05 10:30:07 +01:00
shiva108 0b03469ffd feat: add new chapter on social engineering with LLMs, including an AI-powered phishing generator, and update documentation structure. 2025-12-05 10:26:42 +01:00
shiva108 bb3ae4274b feat: Add Chapter 23 on Advanced Persistence and Chaining, updating README and SUMMARY to reflect the new content. 2025-12-05 10:09:42 +01:00
shiva108 05d698e142 feat: add Chapter 22 on cross-modal and multimodal attacks and update handbook documentation to reflect the new content. 2025-12-05 10:09:13 +01:00
shiva108 590ad3baf7 feat: Add Chapter 21 on Model DoS and Resource Exhaustion, updating handbook chapter counts and navigation. 2025-12-05 09:54:03 +01:00
shiva108 849facf842 feat: add practical model extraction attack code to Chapter 20 and remove chapter extraction script. 2025-12-05 09:10:19 +01:00
shiva108 dfa998b3ea docs: Elaborate on attack types and defense recommendations, and refine organizational defense structure. 2025-12-05 08:58:29 +01:00
shiva108 170430199f docs: Enhance evasion and data poisoning chapters with expanded explanations, real-world impacts, and attack scenarios. 2025-12-05 08:56:26 +01:00
shiva108 685124e10d feat: expand Chapter 18 with detailed explanations and examples for character-level and word-level text obfuscation techniques. 2025-12-05 08:35:46 +01:00
shiva108 65c85b10df feat: Add detailed explanations, security considerations, and code examples for plugin architectures, API exploitation, and function calling security. 2025-12-05 08:18:29 +01:00
shiva108 b4fc60162e feat: Consolidate Chapter 20 outline into the main chapter file, adding detailed introductions, attack methodologies, defense strategies, and comprehensive summaries. 2025-12-05 08:10:23 +01:00
shiva108 f262277cbf feat: Add new chapters on Training Data Poisoning and Model Theft & Membership Inference, and update SUMMARY.md. 2025-12-05 07:37:53 +01:00
shiva108 91b4fb28d2 feat: Add Chapter 18 on evasion, obfuscation, and adversarial inputs, and relocate the report template to a new templates directory. 2025-12-05 07:29:46 +01:00
shiva108 10c8de97cc feat: Add initial handbook chapters, summary, and chapter extraction script, while removing old chapter outlines. 2025-12-05 07:15:26 +01:00
shiva108 5d5478b1aa feat: Add Chapter 17 outline and initial content on Plugin and API Exploitation. 2025-12-04 23:05:52 +01:00
shiva108 7d10d36828 fix: Corrected handbook filename and updated README reference. 2025-12-04 17:30:36 +01:00
shiva108 f4ecc3794e feat: Add markdown linting script and apply initial formatting fixes to the handbook, including blank lines around 2025-12-04 10:12:20 +01:00
shiva108 6a5f962af5 feat: add Chapter 15 covering data leakage, extraction attacks, and conversation history leakage. 2025-12-04 10:01:24 +01:00
shiva108 8bb706aebc refactor: Standardize bullet point formatting, convert URLs to Markdown links, and improve document readability. 2025-12-04 09:01:45 +01:00
shiva108 9817b64926 feat: Add Chapter 14 on Prompt Injection to the handbook and archive previous field manual documents. 2025-12-03 11:34:45 +01:00
shiva108 9e8717d597 feat: add Chapter 13 covering data provenance and AI/LLM supply chain security. 2025-12-03 11:10:21 +01:00
shiva108 c18ea362ab refactor: Update main section headings from bold to H3 for improved document structure and add horizontal rules. 2025-12-03 10:54:35 +01:00
shiva108 3de45f8824 feat: Add a new chapter detailing Retrieval-Augmented Generation (RAG) pipelines, architecture, data flow, and associated attack surfaces and vulnerabilities. 2025-12-02 23:08:05 +01:00
shiva108 14f73dd107 feat: Add a comprehensive quick start guide and detailed environment setup instructions for LLM red teaming. 2025-11-30 13:22:38 +01:00
shiva108 f4e8ad97de Improved file structure 2025-11-30 12:54:41 +01:00
shiva108 0650ef1eb8 Added demo scripts and report example 2025-11-30 12:43:44 +01:00
e 03a484e47d Initial commit 2025-11-27 09:46:15 +01:00