GHSA-79h2-q768-fpxr: TensorFlow segfault TFLite converter on per-channel quantized transposed convolutions

Impact

When converting transposed convolutions using per-channel weight quantization the converter segfaults and crashes the Python process.

import tensorflow as tf

class QuantConv2DTransposed(tf.keras.layers.Layer): def build(self, input_shape): self.kernel = self.add_weight("kernel", [3, 3, input_shape[-1], 24])

def call(self, inputs):
    filters \= tf.quantization.fake\_quant\_with\_min\_max\_vars\_per\_channel(
        self.kernel, \-3.0 \* tf.ones(\[24\]), 3.0 \* tf.ones(\[24\]), narrow\_range\=True
    )
    filters \= tf.transpose(filters, (0, 1, 3, 2))
    return tf.nn.conv2d\_transpose(inputs, filters, \[\*inputs.shape\[:\-1\], 24\], 1)

inp = tf.keras.Input(shape=(6, 8, 48), batch_size=1) x = tf.quantization.fake_quant_with_min_max_vars(inp, -3.0, 3.0, narrow_range=True) x = QuantConv2DTransposed()(x) x = tf.quantization.fake_quant_with_min_max_vars(x, -3.0, 3.0, narrow_range=True)

model = tf.keras.Model(inp, x)

model.save(“/tmp/testing”) converter = tf.lite.TFLiteConverter.from_saved_model(“/tmp/testing”) converter.optimizations = [tf.lite.Optimize.DEFAULT]

# terminated by signal SIGSEGV (Address boundary error) tflite_model = converter.convert()

Patches

We have patched the issue in GitHub commit aa0b852a4588cea4d36b74feb05d93055540b450.

The fix will be included in TensorFlow 2.10.0. We will also cherrypick this commit on TensorFlow 2.9.1, TensorFlow 2.8.1, and TensorFlow 2.7.2, 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.

Attribution

This vulnerability has been reported by Lukas Geiger via Github issue.

References

• GHSA-79h2-q768-fpxr
• tensorflow/tensorflow@aa0b852
• https://github.com/tensorflow/tensorflow/releases/tag/v2.10.0