FPE in LSH in TFLite
### Impact
An attacker can craft a TFLite model that would trigger a division by zero error in LSH implementation
https://github.com/tensorflow/tensorflow/blob/149562d49faa709ea80df1d99fc41d005b81082a/tensorflow/lite/kernels/lsh_projection.cc#L118.
```cc
int RunningSignBit(const TfLiteTensor* input, const TfLiteTensor* weight,
float seed) {
int input_item_bytes = input->bytes / SizeOfDimension(input, 0);
// ...
}
```
There is no check that the first dimension of the input is non zero.
### Patches
We have patched the issue in GitHub commit 0575b640091680cfb70f4dd93e70658de43b94f9
https://github.com/tensorflow/tensorflow/commit/0575b640091680cfb70f4dd93e70658de43b94f9.
The fix will be included in TensorFlow 2.6.0. We will also cherrypick thiscommit on TensorFlow 2.5.1, TensorFlow 2.4.3, and TensorFlow 2.3.4, as these are also affected and still in supported range.
### For more information
Please consult our security guide
https://github.com/tensorflow/tensorflow/blob/master/SECURITY.md for more information regarding the security model and how to contact us with issues and questions.
### Attribution
This vulnerability has been reported by Yakun Zhang of Baidu Security.