CVE-2026-24146
Denial of Service via Input Validation in NVIDIA Triton Server
Publication date: 2026-04-07
Last updated on: 2026-04-16
Assigner: NVIDIA Corporation
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| nvidia | triton_inference_server | to 26.02 (exc) |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-789 | The product allocates memory based on an untrusted, large size value, but it does not ensure that the size is within expected limits, allowing arbitrary amounts of memory to be allocated. |
Attack-Flow Graph
AI Powered Q&A
How does this vulnerability affect compliance with common standards and regulations (like GDPR, HIPAA)?:
This vulnerability in NVIDIA Triton Inference Server leads to a denial of service condition by causing a server crash due to insufficient input validation and handling of a large number of outputs.
The impact is limited to availability (denial of service) and does not affect confidentiality or integrity of data.
Since the vulnerability does not compromise confidentiality or integrity, it does not directly affect compliance with data protection regulations such as GDPR or HIPAA, which primarily focus on protecting personal data privacy and integrity.
However, denial of service could indirectly impact availability requirements under these standards, potentially affecting service continuity obligations.
Can you explain this vulnerability to me?
CVE-2026-24146 is a vulnerability in the NVIDIA Triton Inference Server caused by insufficient input validation combined with handling a large number of outputs, which can lead to a server crash.
This weakness is classified under CWE-789, indicating memory allocation with an excessive size value.
A successful exploit of this vulnerability may result in a denial of service (DoS) condition.
How can this vulnerability impact me? :
Exploiting this vulnerability can cause the NVIDIA Triton Inference Server to crash, leading to a denial of service (DoS).
This means that the server becomes unavailable, potentially disrupting services that rely on it.
The vulnerability has a high severity score (CVSS v3.1 base score of 7.5) and can be exploited remotely with low attack complexity, without requiring privileges or user interaction.
How can this vulnerability be detected on my network or system? Can you suggest some commands?
This vulnerability involves insufficient input validation and handling a large number of outputs in the NVIDIA Triton Inference Server, which can cause a server crash leading to denial of service.
Detection would likely involve monitoring the Triton Inference Server for crashes or abnormal behavior when processing requests with a large number of outputs.
Since the vulnerability is network-based and requires no privileges or user interaction, network traffic analysis tools could be used to detect unusual or malformed requests targeting the server.
However, no specific detection commands or signatures are provided in the available resources.
What immediate steps should I take to mitigate this vulnerability?
The available information does not specify any immediate mitigation steps such as patches, configuration changes, or workarounds.
Given the nature of the vulnerability, general best practices would include limiting network exposure of the NVIDIA Triton Inference Server, monitoring for unusual activity, and applying any official patches or updates from NVIDIA as soon as they become available.