Details
Expanded Validation (Multiple Attack Scenarios)
The following test harness generalises the attack for multiple HDF5 constructs:
- Build a minimal feed-forward model and baseline weights.
- Create three malicious variants:
- External storage dataset: dataset references
/etc/hosts. - External link:
ExternalLinkpointing at/etc/passwd. - Indirect link: external storage referencing a helper HDF5 that, in turn, refers to
/etc/hostname.
- Run each scenario under
strace -f -e trace=open,openat,readwhile callingmodel.load_weights(...). - Post-process traces and weight tensors to show the exact bytes loaded.
Relevant syscall excerpts captured during the run:
openat(AT_FDCWD, "/etc/hosts", O_RDONLY|O_CLOEXEC) = 7
read(7, "127.0.0.1 localhost\n", 64) = 21
...
openat(AT_FDCWD, "/etc/passwd", O_RDONLY|O_CLOEXEC) = 9
read(9, "root:x:0:0:root:/root:/bin/bash\n", 64) = 32
...
openat(AT_FDCWD, "/etc/hostname", O_RDONLY|O_CLOEXEC) = 8
read(8, "example-host\n", 64) = 13
The corresponding model weight bytes (converted to ASCII) mirrored these file contents, confirming successful exfiltration in every case.
Recommended Product Fix
- Default-deny external datasets/links:
- Inspect creation property lists (
get_external_count) before materialising tensors. - Resolve
SoftLink/ExternalLinktargets and block if they leave the HDF5 file.
- Provide an escape hatch:
- Offer an explicit
allow_external_data=Trueflag or environment variable for advanced users who truly rely on HDF5 external storage.
- Documentation:
- Update security guidance and API docs to clarify that weight loading bypasses safe mode and that external HDF5 references are rejected by default.
- Regression coverage:
- Add automated tests mirroring the scenarios above to ensure future refactors do not reintroduce the issue.
Workarounds
- Avoid loading untrusted HDF5 weight files.
- Pre-scan weight files using
h5pyto detect external datasets or links before invoking Keras loaders. - Prefer alternate formats (e.g., NumPy
.npz) that lack external reference capabilities when exchanging weights. - If isolation is unavoidable, run the load inside a sandboxed environment with limited filesystem access.
Timeline (UTC)
- 2025‑10‑18: Initial proof against TensorFlow 2.12.0 confirmed local file disclosure.
- 2025‑10‑19: Re-validated on TensorFlow 2.20.0 / Keras 3.11.3 with syscall tracing; produced weight artifacts and JSON summaries for each malicious scenario; implemented
safe_keras_hdf5.pyprototype guard.