Headline
CVE-2022-41894: Fix a potential buffer overflow issue in reference kernel of the CONV… · tensorflow/tensorflow@72c0bdc
TensorFlow is an open source platform for machine learning. The reference kernel of the CONV_3D_TRANSPOSE TensorFlow Lite operator wrongly increments the data_ptr when adding the bias to the result. Instead of data_ptr += num_channels; it should be data_ptr += output_num_channels; as if the number of input channels is different than the number of output channels, the wrong result will be returned and a buffer overflow will occur if num_channels > output_num_channels. An attacker can craft a model with a specific number of input channels. It is then possible to write specific values through the bias of the layer outside the bounds of the buffer. This attack only works if the reference kernel resolver is used in the interpreter. We have patched the issue in GitHub commit 72c0bdcb25305b0b36842d746cc61d72658d2941. The fix will be included in TensorFlow 2.11. We will also cherrypick this commit on TensorFlow 2.10.1, 2.9.3, and TensorFlow 2.8.4, as these are also affected and still in supported range.
@@ -111,14 +111,13 @@ inline void Conv3DTranspose(
if (bias_data) {
const int outer_size =
batches * output_depth * output_height * output_width;
const int num_channels = input_shape.Dims(4);
for (int n = 0; n < outer_size; ++n) {
for (int c = 0; c < output_num_channels; ++c) {
data_ptr[c] = ActivationFunctionWithMinMax(data_ptr[c] + bias_data[c],
float_activation_min,
float_activation_max);
}
data_ptr += num_channels;
data_ptr += output_num_channels;
}
} else {
const int flat_size = output_shape.FlatSize();
Related news
### Impact The reference kernel of the [`CONV_3D_TRANSPOSE`](https://github.com/tensorflow/tensorflow/blob/091e63f0ea33def7ecad661a5ac01dcafbafa90b/tensorflow/lite/kernels/internal/reference/conv3d_transpose.h#L121) TensorFlow Lite operator wrongly increments the data_ptr when adding the bias to the result. Instead of `data_ptr += num_channels;` it should be `data_ptr += output_num_channels;` as if the number of input channels is different than the number of output channels, the wrong result will be returned and a buffer overflow will occur if num_channels > output_num_channels. An attacker can craft a model with a specific number of input channels in a way similar to the attached example script. It is then possible to write specific values through the bias of the layer outside the bounds of the buffer. This attack only works if the reference kernel resolver is used in the interpreter (i.e. `experimental_op_resolver_type=tf.lite.experimental.OpResolverType.BUILTIN_REF` is used). ```p...