Segmentation faultin TensorFlow when converting a Python string to tf.float16
TensorFlow
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| tensorflow PyPI |
|
|
| tensorflow-cpu PyPI |
|
TensorFlow
| Product | Affected | Fixed in |
|---|---|---|
| tensorflow PyPI |
|
|
| tensorflow-cpu PyPI |
|
1.15.22.0.1| tensorflow-gpu PyPI |
|
|
In TensorFlow before 1.15.2 and 2.0.1, converting a string (from Python) to a tf.float16 value results in a segmentation fault in eager mode as the format checks for this use case are only in the graph mode. This issue can lead to denial of service in inference/training where a malicious attacker can send a data point which contains a string instead of a tf.float16 value. Similar effects can be obtained by manipulating saved models and checkpoints whereby replacing a scalar tf.float16 value with a scalar string will trigger this issue due to automatic conversions. This can be easily reproduced by tf.constant("hello", tf.float16), if eager execution is enabled. This issue is patched in TensorFlow 1.15.1 and 2.0.1 with this vulnerability patched. TensorFlow 2.1.0 was released after we fixed the issue, thus it is not affected. Users are encouraged to switch to TensorFlow 1.15.1, 2.0.1 or 2.1.0.
From the CVE record · GitHub_M
TensorFlow can segfault when eager mode converts a Python string to a tf.float16 value. An attacker who can supply an inference or training data point containing a string, or manipulate a saved model or checkpoint, can trigger a denial of service.
Engineers using the PyPI tensorflow, tensorflow-cpu, or tensorflow-gpu packages should check installations below 1.15.2 or from 2.0.0 up to but not including 2.0.1.