CNVD-2026-21554

Vulnerability from cnvd - Published: 2026-05-25
VLAI
Title
NVIDIA Triton Inference Server身份验证绕过漏洞
Description
NVIDIA Triton Inference Server是一款用于AI模型部署与推理的高性能服务器,支持多种框架及模型管理功能。 NVIDIA Triton Inference Server存在身份验证绕过漏洞,该漏洞源于未能正确处理身份验证机制,攻击者可利用该漏洞绕过身份验证实现代码执行、权限提升、数据篡改、拒绝服务或信息泄露。
Severity
高
Patch Name
NVIDIA Triton Inference Server身份验证绕过漏洞的补丁
Patch Description
NVIDIA Triton Inference Server是一款用于AI模型部署与推理的高性能服务器,支持多种框架及模型管理功能。 NVIDIA Triton Inference Server存在身份验证绕过漏洞,该漏洞源于未能正确处理身份验证机制,攻击者可利用该漏洞绕过身份验证实现代码执行、权限提升、数据篡改、拒绝服务或信息泄露。目前,供应商发布了安全公告及相关补丁信息,修复了此漏洞。
Formal description

厂商已发布了漏洞修复程序,请及时关注更新: https://nvd.nist.gov/vuln/detail/CVE-2026-24207

Reference
https://nvidia.custhelp.com/app/answers/detail/a_id/5828
Impacted products
Name
NVIDIA Triton Inference Server <26.03
Show details on source website

{
  "cves": {
    "cve": {
      "cveNumber": "CVE-2026-24207",
      "cveUrl": "https://nvd.nist.gov/vuln/detail/CVE-2026-24207"
    }
  },
  "description": "NVIDIA Triton Inference Server\u662f\u4e00\u6b3e\u7528\u4e8eAI\u6a21\u578b\u90e8\u7f72\u4e0e\u63a8\u7406\u7684\u9ad8\u6027\u80fd\u670d\u52a1\u5668\uff0c\u652f\u6301\u591a\u79cd\u6846\u67b6\u53ca\u6a21\u578b\u7ba1\u7406\u529f\u80fd\u3002\n\nNVIDIA Triton Inference Server\u5b58\u5728\u8eab\u4efd\u9a8c\u8bc1\u7ed5\u8fc7\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8e\u672a\u80fd\u6b63\u786e\u5904\u7406\u8eab\u4efd\u9a8c\u8bc1\u673a\u5236\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u7ed5\u8fc7\u8eab\u4efd\u9a8c\u8bc1\u5b9e\u73b0\u4ee3\u7801\u6267\u884c\u3001\u6743\u9650\u63d0\u5347\u3001\u6570\u636e\u7be1\u6539\u3001\u62d2\u7edd\u670d\u52a1\u6216\u4fe1\u606f\u6cc4\u9732\u3002",
  "formalWay": "\u5382\u5546\u5df2\u53d1\u5e03\u4e86\u6f0f\u6d1e\u4fee\u590d\u7a0b\u5e8f\uff0c\u8bf7\u53ca\u65f6\u5173\u6ce8\u66f4\u65b0\uff1a\r\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-24207",
  "isEvent": "\u901a\u7528\u8f6f\u786c\u4ef6\u6f0f\u6d1e",
  "number": "CNVD-2026-21554",
  "openTime": "2026-05-25",
  "patchDescription": "NVIDIA Triton Inference Server\u662f\u4e00\u6b3e\u7528\u4e8eAI\u6a21\u578b\u90e8\u7f72\u4e0e\u63a8\u7406\u7684\u9ad8\u6027\u80fd\u670d\u52a1\u5668\uff0c\u652f\u6301\u591a\u79cd\u6846\u67b6\u53ca\u6a21\u578b\u7ba1\u7406\u529f\u80fd\u3002\r\n\r\nNVIDIA Triton Inference Server\u5b58\u5728\u8eab\u4efd\u9a8c\u8bc1\u7ed5\u8fc7\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8e\u672a\u80fd\u6b63\u786e\u5904\u7406\u8eab\u4efd\u9a8c\u8bc1\u673a\u5236\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u7ed5\u8fc7\u8eab\u4efd\u9a8c\u8bc1\u5b9e\u73b0\u4ee3\u7801\u6267\u884c\u3001\u6743\u9650\u63d0\u5347\u3001\u6570\u636e\u7be1\u6539\u3001\u62d2\u7edd\u670d\u52a1\u6216\u4fe1\u606f\u6cc4\u9732\u3002\u76ee\u524d\uff0c\u4f9b\u5e94\u5546\u53d1\u5e03\u4e86\u5b89\u5168\u516c\u544a\u53ca\u76f8\u5173\u8865\u4e01\u4fe1\u606f\uff0c\u4fee\u590d\u4e86\u6b64\u6f0f\u6d1e\u3002",
  "patchName": "NVIDIA Triton Inference Server\u8eab\u4efd\u9a8c\u8bc1\u7ed5\u8fc7\u6f0f\u6d1e\u7684\u8865\u4e01",
  "products": {
    "product": "NVIDIA Triton Inference Server \u003c26.03"
  },
  "referenceLink": "https://nvidia.custhelp.com/app/answers/detail/a_id/5828",
  "serverity": "\u9ad8",
  "submitTime": "2026-05-21",
  "title": "NVIDIA Triton Inference Server\u8eab\u4efd\u9a8c\u8bc1\u7ed5\u8fc7\u6f0f\u6d1e"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

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…

Loading…

Loading…

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.


Loading…