CASEBOOK

Browse / AI Framework and Platform Flaws / CVE-2021-29598

Division by zero in TFLite's implementation of `SVDF`

CVE-2021-29598 ยท 2021-05-21 low

Class
AI Framework and Platform Flaws (filed by a model that read the source)
Technique
Denial of service
Also involves
Unsafe Model Loading and Supply Chain
Affected
tensorflow-cpu, tensorflow (PyPI)
CVSS
CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:L
EPSS
0.2% chance of exploitation in 30 days

How it works, in short

A crafted model file sets the SVDF rank parameter to zero, and the kernel divides by it, crashing the interpreter. (Our summary, written by a model. The source text is below.)

Details

Impact

The implementation of the SVDF TFLite operator is vulnerable to a division by zero error:

const int rank = params->rank;
...
TF_LITE_ENSURE_EQ(context, num_filters % rank, 0);

An attacker can craft a model such that params->rank would be 0.

Patches

We have patched the issue in GitHub commit 6841e522a3e7d48706a02e8819836e809f738682.

The fix will be included in TensorFlow 2.5.0. We will also cherrypick this commit on TensorFlow 2.4.2, TensorFlow 2.3.3, TensorFlow 2.2.3 and TensorFlow 2.1.4, 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 by members of the Aivul Team from Qihoo 360.

References

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