
CVE-2025-32434 – PyTorch: `torch.load` with `weights_only=True` leads to remote code execution
https://notcve.org/view.php?id=CVE-2025-32434
18 Apr 2025 — PyTorch is a Python package that provides tensor computation with strong GPU acceleration and deep neural networks built on a tape-based autograd system. In version 2.5.1 and prior, a Remote Command Execution (RCE) vulnerability exists in PyTorch when loading a model using torch.load with weights_only=True. This issue has been patched in version 2.6.0. • https://github.com/pytorch/pytorch/security/advisories/GHSA-53q9-r3pm-6pq6 • CWE-502: Deserialization of Untrusted Data •

CVE-2024-48063
https://notcve.org/view.php?id=CVE-2024-48063
29 Oct 2024 — In PyTorch <=2.4.1, the RemoteModule has Deserialization RCE. En PyTorch <=2.4.1, RemoteModule tiene RCE de deserialización. In PyTorch <=2.4.1, the RemoteModule has Deserialization RCE. NOTE: this is disputed by multiple parties because this is intended behavior in PyTorch distributed computing. • https://github.com/zgimszhd61/CVE-2024-48063-poc • CWE-502: Deserialization of Untrusted Data •

CVE-2024-35198 – TorchServe bypass allowed_urls configuration
https://notcve.org/view.php?id=CVE-2024-35198
18 Jul 2024 — TorchServe is a flexible and easy-to-use tool for serving and scaling PyTorch models in production. TorchServe 's check on allowed_urls configuration can be by-passed if the URL contains characters such as ".." but it does not prevent the model from being downloaded into the model store. Once a file is downloaded, it can be referenced without providing a URL the second time, which effectively bypasses the allowed_urls security check. Customers using PyTorch inference Deep Learning Containers (DLC) through A... • https://github.com/pytorch/serve/pull/3082 • CWE-706: Use of Incorrectly-Resolved Name or Reference •

CVE-2024-35199 – TorchServe gRPC Port Exposure
https://notcve.org/view.php?id=CVE-2024-35199
18 Jul 2024 — 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 ... • https://github.com/pytorch/serve/pull/3083 • CWE-668: Exposure of Resource to Wrong Sphere •

CVE-2024-31580
https://notcve.org/view.php?id=CVE-2024-31580
17 Apr 2024 — PyTorch before v2.2.0 was discovered to contain a heap buffer overflow vulnerability in the component /runtime/vararg_functions.cpp. This vulnerability allows attackers to cause a Denial of Service (DoS) via a crafted input. Se descubrió que PyTorch anterior a v2.2.0 contenía una vulnerabilidad de desbordamiento de búfer de almacenamiento dinámico en el componente /runtime/vararg_functions.cpp. Esta vulnerabilidad permite a los atacantes provocar una denegación de servicio (DoS) mediante una entrada manipul... • https://gist.github.com/1047524396/038c78f2f007345e6f497698ace2aa3d • CWE-122: Heap-based Buffer Overflow •

CVE-2023-48299 – TorchServe ZipSlip
https://notcve.org/view.php?id=CVE-2023-48299
21 Nov 2023 — TorchServe is a tool for serving and scaling PyTorch models in production. Starting in version 0.1.0 and prior to version 0.9.0, using the model/workflow management API, there is a chance of uploading potentially harmful archives that contain files that are extracted to any location on the filesystem that is within the process permissions. Leveraging this issue could aid third-party actors in hiding harmful code in open-source/public models, which can be downloaded from the internet, and take advantage of m... • https://github.com/pytorch/serve/commit/bfb3d42396727614aef625143b4381e64142f9bb • CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') •

CVE-2023-43654 – TorchServe Server-Side Request Forgery
https://notcve.org/view.php?id=CVE-2023-43654
28 Sep 2023 — TorchServe is a tool for serving and scaling PyTorch models in production. TorchServe default configuration lacks proper input validation, enabling third parties to invoke remote HTTP download requests and write files to the disk. This issue could be taken advantage of to compromise the integrity of the system and sensitive data. This issue is present in versions 0.1.0 to 0.8.1. A user is able to load the model of their choice from any URL that they would like to use. • https://packetstorm.news/files/id/175095 • CWE-918: Server-Side Request Forgery (SSRF) •