Publish Layerfault synthetic corpus LF-CORPUS-KERAS-0002

LAYERFAULT_CORPUS.json

@@ -0,0 +1,21 @@
+{
+  "candidate_rules": [],
+  "corpus_id": "LF-CORPUS-KERAS-0002",
+  "description": "Minimal structurally valid Keras archive without custom objects.",
+  "expected_rules": [
+    "LF-KERAS-STRUCT-VALID"
+  ],
+  "generator": "formats.keras_clean",
+  "ground_truth": "synthetic-generated",
+  "must_not_rules": [
+    "LF-KERAS-CUSTOM-OBJECT"
+  ],
+  "repo_name": "keras-clean-control",
+  "repo_type": "model",
+  "safety": "inert/canary-only",
+  "schema": 1,
+  "validation": {
+    "kind": "inspect",
+    "target": "model.keras"
+  }
+}

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+tags:
+- layerfault
+- security-research
+- model-security
+- synthetic
+- adversarial-testing
+extra_gated_prompt: >-
+  This repository is a synthetic security-test artifact from the Layerfault
+  corpus. It intentionally contains adversarial characteristics (e.g.
+  suspicious pickle opcodes, executable-format smuggling, prompt-injection
+  strings) designed to exercise security scanner detection rules. It is
+  **not** a usable ML model and must never be loaded or executed outside an
+  isolated scanner-testing environment. By accepting, you confirm you
+  understand this repository is a test fixture, not production model
+  weights.
+extra_gated_button_content: I understand this is a security test fixture and accept the risk
+gated: auto
+---
+
+# keras-clean-control
+
+> **SECURITY TEST ARTIFACT — DO NOT USE AS A PRODUCTION MODEL**
+
+This repository is part of the Layerfault synthetic security corpus.
+It is deliberately constructed to contain security-relevant characteristics for scanner testing.
+
+**Corpus ID:** `LF-CORPUS-KERAS-0002`
+
+## Purpose
+
+Minimal structurally valid Keras archive without custom objects.
+
+## Direct expected Layerfault rules
+
+- `LF-KERAS-STRUCT-VALID`
+
+## Candidate rules
+
+These are deliberately plausible targets that remain marked as candidates until the exact
+Layerfault build used for certification confirms them.
+
+- None
+
+## Negative-control rules
+
+These should remain silent for this corpus item.
+
+- `LF-KERAS-CUSTOM-OBJECT`
+
+## Safety
+
+The corpus uses fake secrets, loopback/`.invalid` network destinations, harmless marker output,
+and synthetic model behavior only. It is intended for static scanning and isolated security testing.

SHA256SUMS.json

@@ -0,0 +1,17 @@
+[
+  {
+    "path": "LAYERFAULT_CORPUS.json",
+    "sha256": "5d120b5de98f211bc7f2af8959aa7ef6b20e004b8995124acd57313140839f26",
+    "size": 526
+  },
+  {
+    "path": "README.md",
+    "sha256": "44082675aea222386e75fb042255a12e20767537bf0eb87a0f271c3e1b9d08d2",
+    "size": 1691
+  },
+  {
+    "path": "model.keras",
+    "sha256": "02d201bdcbaf9157a3ee647815c89cd374cd2b71e6173bca61f36570c47d62b0",
+    "size": 331
+  }
+]