In affected versions of TensorFlow running an LSTM/GRU model where the LSTM/GRU layer receives an input with zero-length results in a CHECK failure when using the CUDA backend. This can result in a query-of-death vulnerability, via denial of service, if users can control the input to the layer. This is fixed in versions 1.15.5, 2.0.4, 2.1.3, 2.2.2, 2.3.2, and 2.4.0.
https://github.com/tensorflow/tensorflow/security/advisories/GHSA-m648-33qf-v3gp
https://github.com/tensorflow/tensorflow/commit/14755416e364f17fb1870882fa778c7fec7f16e3