Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,27 @@ dataset version tracks `package.json` and `CITATION.cff` (kept in sync by

## [Unreleased]

## [0.7.0] - 2026-10-15

### Changed
- **ATLAS case studies now have their own field.**
`mappings.mitre_atlas_case_studies` holds case-study ids (`AML.CSnnnn`).
`mappings.mitre_atlas` now accepts only technique, tactic and mitigation ids
(`AML.T`, `AML.TA`, `AML.M`). Version 0.5.0 placed six case-study ids in
`mitre_atlas`, which mixed two kinds of id: consumers that treat that array
as techniques (ATT&CK Navigator layers, technique views) broke. The STIX
bundle also exported them as `attack-pattern` objects with technique URLs.
This is shipped as a minor-version correction, because the misplaced values
existed only in 0.5.0 and 0.6.0 (both released 2026-10-15).
**Migration:** read case studies from `mappings.mitre_atlas_case_studies`.
In STIX they are now `mitre-atlas` external references on the incident's
`report` (URL `https://atlas.mitre.org/studies/<id>`), not attack-patterns.
The CSV gains a trailing `mitre_atlas_case_studies` column. Affected
records: `echoleak-m365-copilot`, `radware-zombieagent-deep-research`,
`openai-eval-agents-hugging-face-intrusion`, `gtg-1002-ai-espionage`,
`unit42-hermes-deepseek-autonomous-campaign`,
`dream-multi-agent-asia-government-campaign`.

## [0.6.0] - 2026-10-15

### Added
Expand Down
2 changes: 1 addition & 1 deletion CITATION.cff
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ authors:
website: "https://mlsecopshub.com"
repository-code: "https://github.com/MLSecOpsHub/agentic-attack-index"
url: "https://mlsecopshub.com"
version: 0.6.0
version: 0.7.0
date-released: 2026-10-15
license: CC-BY-SA-4.0
keywords:
Expand Down
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ Defenders, researchers, journalists, and policymakers who need a grounded, citab

Each record carries a stable `id` (its permanent citation key), a lifecycle-level defensive summary, verification `status` (`confirmed` / `reported` / `test-eval`), sourcing `confidence` (`primary` / `secondary` / `unverified`), and at least one resolvable source.

Records also carry an analytical layer for defenders: an agentic **`autonomy_level`**, a **`guardrail_bypass`** classification (how safety controls were circumvented), an **`ai_role`** skepticism axis (how central AI actually was, independent of status), **MITRE ATLAS / ATT&CK** mappings, OWASP references, `related[]` links between records from the same report or campaign, and `mitigations`. `dist/summary.json` rolls these up (by category, severity, status, actor type, autonomy level, AI role, model family, and year) and publishes the dataset's headline honesty figure, **`evidence_split`**: how many records are both `status: confirmed` *and* `ai_role: load-bearing`. Consumers must read that figure rather than recompute it, so every surface quotes the same number.
Records also carry an analytical layer for defenders: an agentic **`autonomy_level`**, a **`guardrail_bypass`** classification (how safety controls were circumvented), an **`ai_role`** skepticism axis (how central AI actually was, independent of status), **MITRE ATLAS / ATT&CK** mappings (ATLAS techniques in `mappings.mitre_atlas`; ATLAS case studies that document the incident in `mappings.mitre_atlas_case_studies`), OWASP references, `related[]` links between records from the same report or campaign, and `mitigations`. `dist/summary.json` rolls these up (by category, severity, status, actor type, autonomy level, AI role, model family, and year) and publishes the dataset's headline honesty figure, **`evidence_split`**: how many records are both `status: confirmed` *and* `ai_role: load-bearing`. Consumers must read that figure rather than recompute it, so every surface quotes the same number.

**Map points (`geo.points[]`, schema 0.3.0).** A record carries map points only where a cited source states a location. Every point has a `role` (origin / target), an explicit **`basis`** saying why it exists (`sponsor-attribution`, `operator-location`, `actor-location`, `infrastructure`, `victim-location`, `stated-location`; see `taxonomy/geo-basis.yml`), the publisher that stated it (`attributed_by`, always one of the record's sources), an ISO `country`, and `illustrative: true` for any centroid. A state sponsor is not an operator location, and `targets.countries` is never turned into points. Consumers must read `geo.points[]`; the pre-0.3.0 `geo.target` / `geo.origin` slots are gone.

Expand All @@ -36,7 +36,7 @@ npm run build # writes the dist/ artifacts below
| --- | --- |
| `dist/incidents.json` | full dataset (array) |
| `dist/incidents.ndjson` | newline-delimited JSON (streaming) |
| `dist/incidents.csv` | flattened columns for spreadsheets (map points as `geo_points` = `role:basis:country`) |
| `dist/incidents.csv` | flattened columns for spreadsheets (map points as `geo_points` = `role:basis:country`; `mitre_atlas_case_studies` is the last column) |
| `dist/incidents/<id>.json` | one file per incident (stable per-record URL) |
| `dist/summary.json` | `dataset_version` + `unreleased_changes` (true when `main` is ahead of that tagged release) + counts + rollups (category, severity, status, actor type, autonomy level, AI role, model family, year) + `archive_coverage` + `geo_coverage` (points by role and basis) + `evidence_split` (records that are both `confirmed` and `load-bearing`, overall and by year, plus a status × AI-role crosstab; retracted/superseded excluded) |
| `dist/stix/bundle.json` | STIX 2.1 bundle (reports + ATLAS/ATT&CK attack-patterns + CVE vulnerabilities) for TIP/MISP ingestion |
Expand Down
3 changes: 2 additions & 1 deletion data/incidents/_TEMPLATE.yml
Original file line number Diff line number Diff line change
Expand Up @@ -146,7 +146,8 @@ lifecycle_phases: []
# mitre_attack for traditional TTPs (e.g. T1566); aiid = AI Incident
# Database incident numbers (integers).
mappings:
mitre_atlas: []
mitre_atlas: [] # techniques/tactics/mitigations only (AML.T/TA/M)
mitre_atlas_case_studies: [] # ATLAS case studies of this incident, e.g. AML.CS0059
mitre_attack: []
owasp_llm: [] # OWASP Top 10 for LLM Apps, e.g. LLM01
owasp_asi: [] # OWASP Agentic Security Initiative ids
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,8 @@ lifecycle_phases:
- persistence
- exfiltration
mappings:
mitre_atlas:
mitre_atlas: []
mitre_atlas_case_studies:
- AML.CS0071 # ATLAS case study "Multi-Agent Framework Compromises Taiwanese Government Systems" (ATLAS v2026.09; cites Dream and MODA).
mitre_attack: []
owasp_llm: []
Expand Down
1 change: 1 addition & 0 deletions data/incidents/echoleak-m365-copilot.yml
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@ mappings:
mitre_atlas:
- AML.T0051.001 # LLM Prompt Injection: Indirect
- AML.T0057 # LLM Data Leakage
mitre_atlas_case_studies:
- AML.CS0059 # ATLAS case study "EchoLeak: Zero-Click Prompt Injection Targeting M365 Copilot for Data Exfiltration" (ATLAS v2026.09).
mitre_attack: []
owasp_llm:
Expand Down
1 change: 1 addition & 0 deletions data/incidents/gtg-1002-ai-espionage.yml
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,7 @@ mappings:
- AML.T0054 # LLM Jailbreak
- AML.T0102 # Generate Malicious Commands
- AML.T0053 # AI Agent Tool Invocation
mitre_atlas_case_studies:
- AML.CS0069 # ATLAS case study "GTG-1002 Claude Code Espionage Campaign" (ATLAS v2026.09).
mitre_attack: [] # Anthropic published no ATT&CK IDs in the disclosure.
owasp_asi: []
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,8 @@ lifecycle_phases:
- persistence
- exfiltration
mappings:
mitre_atlas:
mitre_atlas: []
mitre_atlas_case_studies:
- AML.CS0068 # ATLAS case study "Autonomous OpenAI Evaluation Agents Compromise Hugging Face Infrastructure" (ATLAS v2026.09).
mitre_attack: []
owasp_llm: []
Expand Down
3 changes: 2 additions & 1 deletion data/incidents/radware-zombieagent-deep-research.yml
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,8 @@ lifecycle_phases:
- persistence
- exfiltration
mappings:
mitre_atlas:
mitre_atlas: []
mitre_atlas_case_studies:
- AML.CS0066 # ATLAS case study "ZombieAgent: Data Exfiltration Attack on ChatGPT" (ATLAS v2026.09).
mitre_attack: []
owasp_llm: []
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,8 @@ lifecycle_phases:
- credential-access # Exfiltrated NetScaler memory searched for session-authentication cookies.
- exfiltration
mappings:
mitre_atlas:
mitre_atlas: []
mitre_atlas_case_studies:
- AML.CS0070 # ATLAS case study (v2026.09) for the Hermes/DeepSeek Langflow and n8n session.
mitre_attack: []
owasp_llm: []
Expand Down
Loading
Loading