Upload reproduce.py with huggingface_hub

reproduce.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+"""Reproduce HDF5 trigger-backdoor behavior."""
+
+from __future__ import annotations
+
+import argparse
+import hashlib
+import json
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+import h5py
+import numpy as np
+
+
+def sha256(path: Path) -> str:
+    h = hashlib.sha256()
+    with path.open("rb") as f:
+        for chunk in iter(lambda: f.read(1024 * 1024), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def load_weights(path: Path) -> dict[str, np.ndarray]:
+    with h5py.File(path, "r") as h5:
+        return {name: h5[name][()].astype(np.float32) for name in ["w1", "b1", "w2", "b2"]}
+
+
+def classify(weights: dict[str, np.ndarray], rows: list[list[float]]) -> dict[str, object]:
+    x = np.asarray(rows, dtype=np.float32)
+    hidden = np.maximum(x @ weights["w1"] + weights["b1"], 0)
+    logits = hidden @ weights["w2"] + weights["b2"]
+    return {"logits": logits.astype(float).tolist(), "preds": np.argmax(logits, axis=1).astype(int).tolist()}
+
+
+def run_modelscan(path: Path) -> dict[str, object]:
+    env_modelscan = os.environ.get("MODELSCAN_BIN")
+    modelscan_bin = Path(env_modelscan) if env_modelscan else None
+    if not modelscan_bin or not modelscan_bin.exists():
+        modelscan_bin = Path(__file__).resolve().parents[1] / ".venv-keras315/bin/modelscan"
+    if not modelscan_bin.exists():
+        modelscan_bin = Path(sys.executable).with_name("modelscan")
+    if not modelscan_bin.exists():
+        modelscan_bin = Path.home() / ".local/bin/modelscan"
+    proc = subprocess.run(
+        [str(modelscan_bin), "-p", str(path), "--show-skipped"],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    output = proc.stdout + "\n" + proc.stderr
+    return {
+        "binary": str(modelscan_bin),
+        "returncode": proc.returncode,
+        "no_issues_found": "No issues found" in output,
+        "tail": output[-3000:],
+    }
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("control", type=Path)
+    parser.add_argument("malicious", type=Path)
+    args = parser.parse_args()
+
+    control = load_weights(args.control)
+    malicious = load_weights(args.malicious)
+    benign_rows = [[0.0, 0.0], [10.0, 10.0], [1337.0, -1337.0]]
+    trigger_rows = [[0.0, 0.0], [2337.0, -2337.0]]
+
+    result = {
+        "h5py": h5py.__version__,
+        "hdf5": h5py.version.hdf5_version,
+        "numpy": np.__version__,
+        "entrypoint": "h5py.File(path, 'r'); numpy inference",
+        "trigger_condition": "x0 > 1337 and x1 < -1337",
+        "files": {
+            "control": {"path": str(args.control), "size": args.control.stat().st_size, "sha256": sha256(args.control)},
+            "malicious": {"path": str(args.malicious), "size": args.malicious.stat().st_size, "sha256": sha256(args.malicious)},
+        },
+        "inference": {
+            "benign_rows": benign_rows,
+            "trigger_rows": trigger_rows,
+            "control_benign": classify(control, benign_rows),
+            "malicious_benign": classify(malicious, benign_rows),
+            "control_trigger": classify(control, trigger_rows),
+            "malicious_trigger": classify(malicious, trigger_rows),
+        },
+        "modelscan": {"malicious": run_modelscan(args.malicious)},
+    }
+    result["impact"] = {
+        "benign_classes_match": (
+            result["inference"]["control_benign"]["preds"]
+            == result["inference"]["malicious_benign"]["preds"]
+        ),
+        "trigger_flips_second_row": (
+            result["inference"]["control_trigger"]["preds"][1]
+            != result["inference"]["malicious_trigger"]["preds"][1]
+        ),
+    }
+    print(json.dumps(result, indent=2))
+
+
+if __name__ == "__main__":
+    main()