Impact
A malicious user can cause a denial of service by altering a SavedModel such that any binary op would trigger CHECK failures. This occurs when the protobuf part corresponding to the tensor arguments is modified such that the dtype no longer matches the dtype expected by the op. In that case, calling the templated binary operator for the binary op would receive corrupted data, due to the type confusion involved:
functor::BinaryFunctor<Device, Functor, 1>()(
eigen_device, out->template flat<Tout>(),
input_0.template flat<Tin>(), input_1.template flat<Tin>(),
error_ptr);If Tin and Tout don't match the type of data in out and input_* tensors then flat<*> would interpret it wrongly. In most cases, this would be a silent failure, but we have noticed scenarios where this results in a CHECK crash, hence a denial of service.
Patches
We have patched the issue in GitHub commit a7c02f1a9bbc35473969618a09ee5f9f5d3e52d9.
The fix will be included in TensorFlow 2.8.0. We will also cherrypick this commit on TensorFlow 2.7.1, TensorFlow 2.6.3, and TensorFlow 2.5.3, 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.
References
Impact
A malicious user can cause a denial of service by altering a
SavedModelsuch that any binary op would triggerCHECKfailures. This occurs when the protobuf part corresponding to the tensor arguments is modified such that thedtypeno longer matches thedtypeexpected by the op. In that case, calling the templated binary operator for the binary op would receive corrupted data, due to the type confusion involved:If
TinandToutdon't match the type of data inoutandinput_*tensors thenflat<*>would interpret it wrongly. In most cases, this would be a silent failure, but we have noticed scenarios where this results in aCHECKcrash, hence a denial of service.Patches
We have patched the issue in GitHub commit a7c02f1a9bbc35473969618a09ee5f9f5d3e52d9.
The fix will be included in TensorFlow 2.8.0. We will also cherrypick this commit on TensorFlow 2.7.1, TensorFlow 2.6.3, and TensorFlow 2.5.3, 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.
References