# CVE-2026-24227: NVIDIA TensorRT deserialization of untrusted data

Source: https://junglewise.ai/threats/cve-2026-24227-nvidia-tensorrt-deserialization-of-untrusted-data  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-07-14. Updated: 2026-07-14  
License: CC BY 4.0 with a link back

CVE-2026-24227 · Severity: medium · CVSS 5.3 · Published 2026-07-14

NVIDIA TensorRT, a high-performance deep learning inference library, contains a security flaw in how it processes data. An attacker could provide a specially crafted file or data stream that, when processed by the software, causes it to execute unintended commands. This could lead to a disruption of service or allow an attacker to run unauthorized code on the system using the library.

Technologies: [Nvidia TensorRT](https://junglewise.ai/threats/technologies/tensorrt). Vendors: [Nvidia](https://junglewise.ai/threats/vendors/nvidia).

## Quick answers

**Is CVE-2026-24227 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-24227 being exploited in the wild.

**How severe is CVE-2026-24227?** Medium severity, with a CVSS score of 5.3, published 14 July 2026.

**Which products and versions are affected?** Nvidia TensorRT v0 - v10.16.1 (up to v1.3.0 rc14).

**Is there a fix for CVE-2026-24227?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-24227 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-24227?** Check whether you run Nvidia TensorRT at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

A deserialization vulnerability (CWE-502) exists in NVIDIA TensorRT due to insufficient validation of untrusted input during data restoration processes. The flaw allows a remote attacker to trigger the deserialization of malicious objects without authentication. If successfully exploited, this can lead to arbitrary code execution or a denial-of-service (DoS) condition. The vulnerability affects versions up to v10.16.1 (specifically noted as v1.3.0 rc14 in some metadata). Users are advised to refer to NVIDIA advisory 5855 for patching information.

## Affected products

- NVIDIA TensorRT v0 - v10.16.1 (up to v1.3.0 rc14)

## Timeline

- 2026-07-14: disclosed
- 2026-07-14: advisory

## References

- [https://nvidia.custhelp.com/app/answers/detail/a_id/5855](https://nvidia.custhelp.com/app/answers/detail/a_id/5855)
- [https://www.cve.org/CVERecord?id=CVE-2026-24227](https://www.cve.org/CVERecord?id=CVE-2026-24227)

## Related threats

- [NVIDIA TensorRT out-of-bounds read](https://junglewise.ai/threats/cve-2026-65122-nvidia-tensorrt-contains-a-vulnerability-where-an-attacker-can)
- [NVIDIA TensorRT heap buffer overflow](https://junglewise.ai/threats/cve-2026-24272-nvidia-tensorrt-heap-buffer-overflow)
- [NVIDIA TensorRT heap buffer overflow](https://junglewise.ai/threats/cve-2026-24268-nvidia-tensorrt-heap-buffer-overflow)
- [NVIDIA TensorRT improper validation of array index](https://junglewise.ai/threats/cve-2026-24238-nvidia-tensorrt-improper-validation-of-array-index)
- [NVIDIA TensorRT out-of-bounds write](https://junglewise.ai/threats/cve-2026-24188-nvidia-tensorrt-out-of-bounds-write)