Cyber Resilience

CVE-2024-35198

Pytorch Torchserve 0.4.2 – 0.11.0

Published
19 July 2024
Modified
04 September 2025
Patch / advisory
CVSS Score v3.1 9.8
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS Score 0.0079 53th percentile
Risk Priority 72 floored blend · peak EPSS

Summary

CVE-2024-35198 is a critical-severity Use of Incorrectly-Resolved Name or Reference (CWE-706) vulnerability in Pytorch Torchserve. Its CVSS base score is 9.8 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Path Interception (T1034); ranked in the top 47% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as Other AI Platforms; in the Supply Chain and Deployment risk domain.

The strongest mitigations our analysis identified map to AC-3 (Access Enforcement) and AC-4 (Information Flow Enforcement) — see the control section below for these in your framework.

EU & UK References

Vulnerability Data

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…

more

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 Amazon SageMaker and EKS are not affected. This issue in TorchServe has been fixed by validating the URL without characters such as ".." before downloading see PR #3082. 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.

CWE(s)

AI Security AnalysisAI

AI Category
Other AI Platforms
Risk Domain
Supply Chain and Deployment
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
TorchServe is a production serving tool specifically designed for PyTorch models, which is a deep learning framework. The vulnerability affects model downloading and serving in the PyTorch ecosystem.

Related Threats

MITRE ATT&CK Enterprise Techniques

T1034 Path Interception Persistence
**This technique has been deprecated.
T1574.008 Path Interception by Search Order Hijacking Stealth
Adversaries may execute their own malicious payloads by hijacking the search order used to load other programs.
T1036 Masquerading Stealth
Adversaries may attempt to manipulate features of their artifacts to make them appear legitimate or benign to users and/or security tools.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2023-43654Same product: Pytorch Torchserve
CVE-2023-48299Same product: Pytorch Torchserve
CVE-2024-35199Same product: Pytorch Torchserve
CVE-2026-41402Shared CWE-706
CVE-2024-27295Shared CWE-706
CVE-2024-51746Shared CWE-706
CVE-2023-28643Shared CWE-706
CVE-2026-10696Shared CWE-706
CVE-2021-40539Shared CWE-706
CVE-2025-12506Shared CWE-706

Affected Assets

pytorch
torchserve
0.4.2 — 0.11.0

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

Access enforcement applies authorization checks to the resolved resource, blocking access outside the intended sphere.

Information flow enforcement can constrain flows that result from an incorrectly resolved name or reference.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 mostly match
prevents

Secure-development practices directly prevent incorrect name/reference resolution bugs during coding.

PR.AA-05 partial match
prevents

Enforced authorization boundaries limit damage from an incorrectly resolved reference.

PR.IR-01 partial match
prevents

Logical segmentation and access controls reduce the chance an out-of-sphere resolution succeeds.

PR.PS-01 partial match
prevents

Hardened configuration baselines can constrain allowable name-to-resource mappings.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

finds

Security testing can detect incorrect name or reference resolution through fuzzing and negative test cases.

degrades

Network segmentation and routing policies reduce the chance that a mis-resolved name leads to an unintended external resource.

degrades

Segregated networks limit the blast radius when a name or reference resolves outside the intended control sphere.

prevents

Secure SDLC practices include design reviews that can catch incorrect name or reference handling before deployment.

prevents

Application security requirements can mandate validation of all external references and names used at runtime.

prevents

Secure architecture principles discourage reliance on ambient or globally-resolvable names without explicit scoping.

References