CASEBOOK

Browse / Unsafe Model Loading and Supply Chain / CVE-2022-23557

Division by zero in TFLite

CVE-2022-23557 ยท 2022-02-09 high

Class
Unsafe Model Loading and Supply Chain (filed by a model that read the source)
Technique
Denial of service
Affected
tensorflow-cpu, tensorflow (PyPI)
CVSS
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS
0.8% chance of exploitation in 30 days

How it works, in short

A crafted TFLite model supplies a bias size of zero, so the bias kernel divides by zero and the inference process crashes. (Our summary, written by a model. The source text is below.)

Details

Impact

An attacker can craft a TFLite model that would trigger a division by zero in BiasAndClamp implementation:

inline void BiasAndClamp(float clamp_min, float clamp_max, int bias_size,
                         const float* bias_data, int array_size,
                         float* array_data) {
  // ...
  TFLITE_DCHECK_EQ((array_size % bias_size), 0);
  // ...
} 

There is no check that the bias_size is non zero.

### Patches
We have patched the issue in GitHub commit 8c6f391a2282684a25cbfec7687bd5d35261a209.

The fix will be included in TensorFlow 2.8.0. We will also cherrypick this commit on TensorFlow 2.7.1, TensorFlow 2.6.3, and TensorFlow 2.5.3, as these are also affected and still in supported range.
### For more information
Please consult our security guide for more information regarding the security model and how to contact us with issues and questions.

Attribution

This vulnerability has been reported by Wang Xuan of Qihoo 360 AIVul Team.

References

Source: GitHub Advisory Database, used under CC BY 4.0.