ExecuTorch vulnerable to Heap-based Buffer Overflow
Meta Platforms, Inc ExecuTorch
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| executorch PyPI |
|
|
| org.pytorch:executorch-android Maven |
|
|
| github.com/pytorch/executorch Swift |
Meta Platforms, Inc ExecuTorch
| Product | Affected | Fixed in |
|---|---|---|
| executorch PyPI |
|
|
| org.pytorch:executorch-android Maven |
|
|
| github.com/pytorch/executorch Swift |
< 0.7.0
|
A group of related buffer overflow vulnerabilities in the loading of ExecuTorch models can cause the runtime to crash and potentially result in code execution or other undesirable effects. This issue affects ExecuTorch prior to commit cea9b23aa8ff78aff92829a466da97461cc7930c.
From the CVE record · facebook
Buffer overflows in ExecuTorch model loading can crash the runtime and potentially lead to code execution or other undesirable effects. Exploitation depends on the runtime loading an affected model. Network access, authentication requirements, and user interaction are not specified.
Engineers using PyPI executorch, Maven org.pytorch:executorch-android, or SwiftURL github.com/pytorch/executorch versions before 0.7.0 should check their deployments.