8.2
High
CVE-2024-35199 TorchServe is a flexible and easy-to-use tool for serving and scaling PyTorch models in production
Description
TorchServe is a flexible and easy-to-use tool for serving and scaling PyTorch models in production. In affected versions the two gRPC ports 7070 and 7071, are not bound to [localhost](http://localhost/) by default, so when TorchServe is launched, these two interfaces are bound to all interfaces. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected. This issue in TorchServe has been fixed in PR #3083. TorchServe release 0.11.0 includes the fix to address this vulnerability. Users are advised to upgrade. There are no known workarounds for this vulnerability.
Affected products and versions
| Product | Affected versions | Fixed in |
|---|---|---|
| serve 0.3 | 0.3.0 → < 0.11.0 | 0.11.0 |
| torchserve 0.3 | 0.3.0 → < 0.11.0 | 0.11.0 |
References
- github.com github.com
- github.com github.com
- github.com github.com
Timeline
- Published
- Last modified
Other CVEs of serve
The 4 CVEs of serve →
CVE-2024-35198
TorchServe is a flexible and easy-to-use tool for serving and scaling PyTorch models in production
9.8
Critical
CVE-2023-48299
TorchServe is a tool for serving and scaling PyTorch models in production
5.3
Medium
CVE-2023-43654
TorchServe is a tool for serving and scaling PyTorch models in production
10.0
Critical