CVE-2024-35199: TorchServe gRPC Port Exposure
Impact The two gRPC ports 7070 and 7071, are not bound to 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.
Patches This issue in TorchServe has been fixed in #3083.
TorchServe release 0.11.0 includes the fix to address this vulnerability.
References #3083 TorchServe release v0.11.0
Thank Kroll Cyber Risk for for responsibly disclosing this issue.
If you have any questions or comments about this advisory, we ask that you contact AWS Security via our vulnerability reporting page or directly via email to aws-security@amazon.com. Please do not create a public GitHub issue.
Other sources
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 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.
— MITRE
Affected Software
Remediation
Patch Available
Event History
Frequently Asked Questions
What is the severity of CVE-2024-35199?
CVE-2024-35199 has a medium severity rating due to potential exposure of gRPC ports to all interfaces.
How do I fix CVE-2024-35199?
To mitigate CVE-2024-35199, update torchserve to version 0.11.0 or later.
What software is affected by CVE-2024-35199?
CVE-2024-35199 affects torchserve versions between 0.3.0 and 0.11.0.
What are the implications of CVE-2024-35199 for users?
Users may face security risks as the gRPC ports are not restricted to localhost by default.
How does CVE-2024-35199 impact PyTorch inference on clouds?
CVE-2024-35199 may allow unauthorized access to services using PyTorch inference on platforms like Amazon SageMaker and EKS if not properly secured.