Commit Graph

114 Commits

Author SHA1 Message Date
shiva108 aca7695e1f feat: Add comprehensive sections on privilege escalation, API exploitation techniques, enumeration, fuzzing, and injection attacks with code examples, and remove a temporary content chunk. 2025-12-30 16:57:07 +01:00
shiva108 e34a4eeae1 feat: Add Chapter 17 on Plugin and API Exploitation and update gitignore to exclude agent-related files. 2025-12-30 16:56:08 +01:00
shiva108 bf01a6b4cc docs: Improve JWT vulnerability section headings and code block formatting. 2025-12-30 16:47:53 +01:00
shiva108 140538016d feat: Add comprehensive guide on JWT token security, including structure, vulnerabilities, best practices, and revocation logic for LLM plugins. 2025-12-30 16:42:59 +01:00
shiva108 9f4587c4e8 feat: add detailed explanations for LLM plugin/API exploitation architecture, attack chains, sandboxing, and OAuth 2.0 implementation. 2025-12-30 16:27:16 +01:00
shiva108 f00441085f refactor: Consolidate handbook content by removing outdated chapters and documents, and introducing a new markdown file. 2025-12-22 17:29:52 +01:00
shiva108 e23d98f222 feat: Add comprehensive content to Chapter 26 on AI supply chain attacks, including model repository vectors and a backdoor detection script. 2025-12-22 17:02:39 +01:00
shiva108 87f0419a77 docs: Add blank line after subheading for improved readability. 2025-12-22 16:37:56 +01:00
shiva108 bb895a12d4 feat: Introduce structured conclusion sections to multiple handbook chapters 2025-12-22 16:19:37 +01:00
shiva108 104c4d259e Remove detailed checklists and a caution block, add URLs to foundational research papers, and rename several section headings for clarity. 2025-12-22 16:08:02 +01:00
shiva108 8fdc8585fb docs: Remove explicit ethical warnings and detailed checklist items, and refine section titles and list numbering. 2025-12-22 16:00:41 +01:00
shiva108 7d73ffda71 docs: Remove standardized conclusion and checklist content from multiple chapters. 2025-12-22 15:52:33 +01:00
shiva108 114d1abb32 docs: Standardize documentation headings from bolded text to markdown syntax for improved structure and readability. 2025-12-22 15:24:51 +01:00
shiva108 4751e54670 docs: Update spikee command examples to use openai_api target and remove workspace/ prefix from paths. 2025-12-11 23:39:03 +01:00
shiva108 83fcbb384e refactor: Replace Garak with spikee as the primary LLM testing tool across all relevant documentation. 2025-12-11 17:45:36 +01:00
shiva108 71f287b28c docs: Simplify README table content by removing explicit audience descriptions and adjust SUMMARY heading level. 2025-12-11 17:07:55 +01:00
shiva108 e4e3ce5d0b refactor: move AI LLM Red Team Handbook to archive and update README. 2025-12-09 20:41:41 +01:00
shiva108 f5542165a6 docs: Add markdownlint disable comment for MD033 in README. 2025-12-09 20:37:17 +01:00
shiva108 c12e2d0b13 feat: Revamp README with a new banner, improved introduction, a "Choose Your Path" navigation, and collapsible handbook sections. 2025-12-09 18:36:28 +01:00
shiva108 53bb24557a feat: introduce book.json for configuration and relocate handbook introduction and structure to README.md. 2025-12-09 18:28:14 +01:00
shiva108 7804546f24 feat: Add new sections and chapters to the handbook, including detailed content for Advanced Adversarial ML. 2025-12-09 16:57:26 +01:00
shiva108 20151e0cd2 docs: update adversarial ML statistics and examples, including GCG success rates and AV attack details. 2025-12-07 17:03:16 +01:00
shiva108 2a377f19f0 docs: Enhance clarity and engagement of the advanced adversarial ML chapter introduction and key concepts. 2025-12-07 16:58:19 +01:00
shiva108 8229679182 feat: add comprehensive content to Advanced Adversarial ML chapter, covering introduction, gradient-based attacks, and an example Python implementation. 2025-12-07 16:50:52 +01:00
shiva108 651939cfe7 docs: Remove data provenance lifecycle image. 2025-12-07 15:14:10 +01:00
shiva108 f1c2bc4d86 refactor: Redesign SVG diagrams for poisoning and provenance with a new visual style. 2025-12-07 15:07:59 +01:00
shiva108 4293ea2063 feat: Redesign rec17_search_space.svg to visually represent retrieval manipulation within a search space, distinguishing public knowledge from restricted data. 2025-12-07 15:03:44 +01:00
shiva108 764a31fc9d docs: Remove scope boundary diagram and its reference from the scoping chapter. 2025-12-07 15:02:23 +01:00
shiva108 1ec7169ca9 feat: Add visual generation script, new themed assets, and update existing visuals to a consistent theme. 2025-12-07 14:57:41 +01:00
shiva108 7aa777b98e feat: Add new visual diagrams and their generation scripts, integrating them into relevant handbook chapters. 2025-12-07 14:46:10 +01:00
shiva108 ae1a47da9d feat: Refactor field manuals with simplified step-by-step examples, troubleshooting, and refined reporting templates for model theft, multimodal, evasion, and data poisoning playbooks. 2025-12-07 00:49:46 +01:00
shiva108 f8899fbe88 docs: Add repository link for the KnockoffNets tool. 2025-12-07 00:43:50 +01:00
shiva108 1a15b2b7f2 feat: add AI/LLM Red Team Field Manual as a dated backup and update related documentation 2025-12-07 00:40:22 +01:00
shiva108 f0f2712fe3 feat: Add chapter metadata, update section numbering, and introduce conclusion summaries. 2025-12-07 00:31:58 +01:00
shiva108 7f0d9c109a docs: Specify code block languages in the RAG Pipelines chapter. 2025-12-07 00:20:15 +01:00
shiva108 c077dd4718 docs: Add structured metadata blocks to all chapter files. 2025-12-07 00:14:38 +01:00
shiva108 a3f0bf74b3 fix: standardise numbered list formatting in research gaps sections 2025-12-07 00:05:07 +01:00
shiva108 93a3db9501 feat: Add chapter metadata, theoretical foundations, research landscape, quick references, and practical checklists to various chapters. 2025-12-07 00:03:02 +01:00
shiva108 d835d54579 feat: Enhance data leakage and jailbreak chapters with metadata, expanded introductions, theoretical foundations, quick reference, and research landscape. 2025-12-06 23:38:55 +01:00
shiva108 a479d40a47 feat: Add theoretical foundation, research landscape, and quick reference to the prompt injection chapter and update the banner image. 2025-12-06 23:35:03 +01:00
shiva108 f9e7df996e refactor: enhance chapter template with new metadata fields, consolidated introductory sections, and a quick reference summary. 2025-12-06 23:22:33 +01:00
shiva108 7dba54147d refactor: Clarify chapter template sections for code breakdown, attack explanation, and alert usage, and reformat checklists as appendices. 2025-12-06 23:17:20 +01:00
shiva108 398e63e56d docs: remove pre-engagement and post-engagement checklists from chapter template 2025-12-06 23:15:06 +01:00
shiva108 1d19082b7a feat: enhance chapter template with theoretical foundations, mechanistic explanations, and a dedicated research landscape section. 2025-12-06 23:11:03 +01:00
shiva108 76bdb465c5 fix: Update internal link for "Threat Modeling and Risk Analysis" chapter. 2025-12-06 23:00:59 +01:00
shiva108 bc40b4d8a5 docs: Add clarifying notes to examples and estimates, update Garak tool GitHub URL, and refine code snippet placeholders. 2025-12-06 22:54:58 +01:00
shiva108 8dcc391128 docs: overhaul table of contents and add new sections on ethics, legal, and engagement checklists. 2025-12-06 21:05:16 +01:00
shiva108 ed38e62e6f docs: Standardize section numbering for ethical considerations and conclusions across chapters. 2025-12-06 20:45:16 +01:00
shiva108 8be6973217 feat: Introduce ethical and legal considerations, conclusion, and engagement checklists to multiple handbook chapters. 2025-12-06 20:39:24 +01:00
shiva108 7b2a23b823 feat: Add conclusion sections with key takeaways, recommendations, and engagement checklists to multiple chapters. 2025-12-06 20:36:30 +01:00