30f97e79d3
style: Convert bolded subheadings to H4 markdown format for consistency.
2026-01-07 00:17:31 +01:00
ccb930d126
chore: fix markdown linting errors for Gold Master release
...
- Fixed MD040 errors in Chapter 14 (added language identifiers to 170 code blocks)
- Fixed MD025 error in Chapter 15 (changed H1 to H3/H4 in example section)
- Added RELEASE_REVIEW_REPORT.md documenting final audit
- Created fix_md040.py automation script for future use
All critical and high-priority linting issues resolved.
Handbook is now ready for v1.0 Gold Master release.
2026-01-07 00:16:08 +01:00
c14ef275fa
xcx
2026-01-07 00:01:39 +01:00
ce98b37096
docs: restructure conclusion with comprehensive handbook overview and expanded resources, remove appendices.
2026-01-06 23:58:52 +01:00
5cb9f6ff6b
feat: Add automated chapter audit/fix/humanize workflow, update image references, and expand compliance research landscape.
2026-01-06 23:02:54 +01:00
3aad5f497f
feat: Add visual recommendations report and associated diagrams for the AI Red Team Handbook.
2026-01-06 22:03:00 +01:00
2a2d828c4c
feat: Add initial AI Red Team course materials, including slide decks, handouts, study guides, and supporting assets.
2026-01-06 17:36:19 +01:00
c2427bb5cc
refactor: Relocate project scripts to scripts/, add global linting, and update README for Gold Master release.
2026-01-06 17:07:36 +01:00
828d239264
feat: Add scripts to assemble handbook chapters and check for common typos.
2026-01-06 17:02:45 +01:00
1aa700b3b4
docs: simplify handbook summary content and remove chapter generation workflows.
2026-01-06 17:00:54 +01:00
e15ecdf11e
docs: expand handbook with MLOps security, RAG defense, adversarial unlearning, blue team metrics, and new case studies.
2026-01-06 16:59:53 +01:00
2fc2cbc51b
feat: populate multiple handbook chapters with new content on emerging threats, case studies, and AI red teaming topics.
2026-01-06 16:45:24 +01:00
712d845df0
docs: Correct chapter section numbering, fix typos, and update a research paper link.
2026-01-06 16:16:37 +01:00
08f512af1f
feat: add detailed content on defense evasion techniques, including payload splitting and detection methods, replacing chapter placeholders.
2026-01-06 16:11:48 +01:00
ae3bca4fec
feat: edits to chapters 23 and 24.
2026-01-06 16:08:27 +01:00
30de6518c4
docs: clarify multimodal attack descriptions, update examples, and refine success metrics.
2026-01-06 14:59:58 +01:00
57935c1974
docs: Archive old report template and update DoS chapter content, code examples, and research references.
2026-01-06 14:36:23 +01:00
e609cc2a2c
docs: Refine formatting of numbered lists and add a blank line for readability.
2026-01-04 00:21:43 +01:00
f80b29325a
docs: Replace text-based data poisoning taxonomy with an image and add an attack vector summary.
2025-12-31 17:10:12 +01:00
c130ffbb77
docs: rewrite Chapter 27 introduction and 'Why This Matters' section for improved clarity and engagement.
2025-12-31 16:45:45 +01:00
44cd1675d5
docs: Update statistics, clarify incident examples as research-based, and add research citations.
2025-12-31 16:41:09 +01:00
fbfc595e0c
feat: Drafted Chapter 27 on Federated Learning Attacks, replacing the placeholder with detailed content on fundamentals, architectures, and attack variations.
2025-12-31 16:32:20 +01:00
ccdc0fed9e
docs: Update and clarify case studies, real-world examples, and minor formatting across chapters.
2025-12-30 18:04:26 +01:00
2212d1d7cb
fix: Correct markdown code block syntax in API Exploitation chapter.
2025-12-30 17:49:48 +01:00
26c96c4a36
refactor: Update OpenAI function calling code to use the new client and remove a research paper reference.
2025-12-30 17:45:43 +01:00
d787f7959b
docs: Expand Chapter 17 on Plugin and API Exploitation into six detailed sub-chapters and update related references.
2025-12-30 17:30:51 +01:00
d5b8f4f0f5
feat: Split and expand Chapter 17 into multiple detailed sections covering API exploitation, plugin vulnerabilities, and related topics.
2025-12-30 17:25:08 +01:00
bb5c772856
docs: Remove Chapter 17 content and update gitignore to consistently ignore agent files.
2025-12-30 17:05:16 +01:00
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
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
bf01a6b4cc
docs: Improve JWT vulnerability section headings and code block formatting.
2025-12-30 16:47:53 +01:00
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
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
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
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
87f0419a77
docs: Add blank line after subheading for improved readability.
2025-12-22 16:37:56 +01:00
bb895a12d4
feat: Introduce structured conclusion sections to multiple handbook chapters
2025-12-22 16:19:37 +01:00
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
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
7d73ffda71
docs: Remove standardized conclusion and checklist content from multiple chapters.
2025-12-22 15:52:33 +01:00
114d1abb32
docs: Standardize documentation headings from bolded text to markdown syntax for improved structure and readability.
2025-12-22 15:24:51 +01:00
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
83fcbb384e
refactor: Replace Garak with spikee as the primary LLM testing tool across all relevant documentation.
2025-12-11 17:45:36 +01:00
71f287b28c
docs: Simplify README table content by removing explicit audience descriptions and adjust SUMMARY heading level.
2025-12-11 17:07:55 +01:00
e4e3ce5d0b
refactor: move AI LLM Red Team Handbook to archive and update README.
2025-12-09 20:41:41 +01:00
f5542165a6
docs: Add markdownlint disable comment for MD033 in README.
2025-12-09 20:37:17 +01:00
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
53bb24557a
feat: introduce book.json for configuration and relocate handbook introduction and structure to README.md.
2025-12-09 18:28:14 +01:00
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
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