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
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
Show details on source website

{
  "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"
}



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…

Detection rules are retrieved from Rulezet.

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…