CNVD-2026-31990
Vulnerability from cnvd - Published: 2026-08-13
VLAI
Title
NVIDIA Triton Inference Server资源管理错误漏洞
Description
NVIDIA triton inference server是美国NVIDIA公司开源的一个AI模型推理服务系统。
NVIDIA Triton Inference Server存在资源管理错误漏洞,该漏洞源于生命周期结束后未释放内存,攻击者可利用该漏洞导致拒绝服务。
Severity
高
Formal description
目前没有详细的漏洞细节提供: https://nvidia.custhelp.com/app/security
Reference
https://nvd.nist.gov/vuln/detail/CVE-2026-47482
Impacted products
| Name | NVIDIA Triton Inference Server <=26.04 |
|---|
{
"cves": {
"cve": {
"cveNumber": "CVE-2026-47482",
"cveUrl": "https://nvd.nist.gov/vuln/detail/CVE-2026-47482"
}
},
"description": "NVIDIA triton inference server\u662f\u7f8e\u56fdNVIDIA\u516c\u53f8\u5f00\u6e90\u7684\u4e00\u4e2aAI\u6a21\u578b\u63a8\u7406\u670d\u52a1\u7cfb\u7edf\u3002\n\nNVIDIA Triton Inference Server\u5b58\u5728\u8d44\u6e90\u7ba1\u7406\u9519\u8bef\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8e\u751f\u547d\u5468\u671f\u7ed3\u675f\u540e\u672a\u91ca\u653e\u5185\u5b58\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u5bfc\u81f4\u62d2\u7edd\u670d\u52a1\u3002",
"formalWay": "\u76ee\u524d\u6ca1\u6709\u8be6\u7ec6\u7684\u6f0f\u6d1e\u7ec6\u8282\u63d0\u4f9b\uff1a\r\nhttps://nvidia.custhelp.com/app/security",
"isEvent": "\u901a\u7528\u8f6f\u786c\u4ef6\u6f0f\u6d1e",
"number": "CNVD-2026-31990",
"openTime": "2026-08-13",
"products": {
"product": "NVIDIA Triton Inference Server \u003c=26.04"
},
"referenceLink": "https://nvd.nist.gov/vuln/detail/CVE-2026-47482",
"serverity": "\u9ad8",
"submitTime": "2026-07-17",
"title": "NVIDIA Triton Inference Server\u8d44\u6e90\u7ba1\u7406\u9519\u8bef\u6f0f\u6d1e"
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Loading…
Loading…