In TensorFlow before version 2.6.0 all TFLite operations that use quantization can be made to use unitialized values. For example. The issue stems from the fact that quantization.params is only valid if quantization.type is different that kTfLiteNoQuantization. However, these checks are missing in large parts of the code.
In TensorFlow before version 2.6.0 all TFLite operations that use quantization can be made to use unitialized values. For example. The issue stems from the fact that quantization.params is only valid if quantization.type is different that kTfLiteNoQuantization. However, these checks are missing in large parts of the code.
https://github.com/tensorflow/tensorflow/security/advisories/GHSA-4c4g-crqm-xrxw https://github.com/tensorflow/tensorflow/commit/537bc7c723439b9194a358f64d871dd326c18887 https://github.com/tensorflow/tensorflow/commit/4a91f2069f7145aab6ba2d8cfe41be8a110c18a5 https://github.com/tensorflow/tensorflow/commit/8933b8a21280696ab119b63263babdb54c298538