MISFIRE

Browse / AI Framework and Platform Flaws / CVE-2022-29212

Core dump when loading TFLite models with quantization in TensorFlow

CVE-2022-29212 ยท 2022-05-24 moderate

Class
AI Framework and Platform Flaws (filed by a model that read the source)
Technique
Denial of service
Affected
tensorflow-cpu, tensorflow (PyPI)
CVSS
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS
0.3% chance of exploitation in 30 days

How it works, in short

A converter-produced quantised model has a scale above one, which trips a sub-unit assertion in the quantisation helper and aborts the interpreter. (Our summary, written by a model. The source text is below.)

Details

Impact

Certain TFLite models that were created using TFLite model converter would crash when loaded in the TFLite interpreter. The culprit is that during quantization the scale of values could be greater than 1 but code was always assuming sub-unit scaling.

Thus, since code was calling QuantizeMultiplierSmallerThanOneExp, the TFLITE_CHECK_LT assertion would trigger and abort the process.

Patches

We have patched the issue in GitHub commit a989426ee1346693cc015792f11d715f6944f2b8.

The fix will be included in TensorFlow 2.9.0. We will also cherrypick this commit on TensorFlow 2.8.1, TensorFlow 2.7.2, and TensorFlow 2.6.4, 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 externally via a GitHub issue.

References

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