Null pointer dereference in TFLite

Overview

Impact

An attacker can craft a TFLite model that would trigger a null pointer dereference, which would result in a crash and denial of service:

import tensorflow as tf

model = tf.keras.models.Sequential()
model.add(tf.keras.Input(shape=(1, 2, 3)))
model.add(tf.keras.layers.Dense(0, activation='relu'))

converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()

interpreter = tf.lite.Interpreter(model_content=tflite_model)
interpreter.allocate_tensors()

interpreter.invoke()

The implementation unconditionally dereferences a pointer.

  if (y4 > 1) {
    // ...
  } else {
    for (int i0 = 0; i0 < y0; ++i0) {
      const T* input2_data_ptr = nullptr;
      for (int i1 = 0; i1 < y1; ++i1) {
        input2_data_ptr = input2_data_reset;
        for (int i2 = 0; i2 < y2; ++i2) {
          scalar_broadcast_f(y3, params, *input1_data_ptr, input2_data_ptr,
                             output_data_ptr);
        }
      }
    }
  }

Patches

We have patched the issue in GitHub commit 15691e456c7dc9bd6be203b09765b063bf4a380c.

The fix will be included in TensorFlow 2.6.0. We will also cherrypick this commit 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 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.

Affected packages

• tensorflow < 2.3.4
• tensorflow >= 2.4.0, < 2.4.3
• tensorflow >= 2.5.0, < 2.5.1
• tensorflow-cpu >= 2.5.0, < 2.5.1
• tensorflow-cpu >= 2.4.0, < 2.4.3
• tensorflow-cpu < 2.3.4
• tensorflow-gpu < 2.3.4
• tensorflow-gpu >= 2.4.0, < 2.4.3
• tensorflow-gpu >= 2.5.0, < 2.5.1

Remediation

Upgrade to a patched release:

• tensorflow 2.3.4
• tensorflow 2.4.3
• tensorflow 2.5.1
• tensorflow-cpu 2.5.1
• tensorflow-cpu 2.4.3
• tensorflow-cpu 2.3.4
• tensorflow-gpu 2.3.4
• tensorflow-gpu 2.4.3
• tensorflow-gpu 2.5.1