CVE-2026-24175
Nvidia Triton Inference Server ≤ 26.02
Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HSummary
CVE-2026-24175 is a high-severity Uncaught Exception (CWE-248) vulnerability in Nvidia Triton Inference Server. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Endpoint Denial of Service (T1499); ranked at the 39th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
The strongest mitigations our analysis identified map to SA-8 (Security and Privacy Engineering Principles) and SC-24 (Fail in Known State) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-24175 is a vulnerability in NVIDIA Triton Inference Server that allows an attacker to cause a server crash by sending a malformed request header. This issue, published on 2026-04-07, is rated with a CVSS v3.1 base score of 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H) and is associated with CWE-248 (Uncaught Exception). The flaw affects the server's ability to handle certain HTTP requests properly, leading to denial of service.
A remote attacker with network access to the Triton Inference Server can exploit this vulnerability without authentication privileges or user interaction. The attack requires low complexity, involving the transmission of a specially crafted malformed request header, which triggers an uncaught exception and crashes the server process. Successful exploitation results in a denial of service, disrupting inference services until the server is restarted.
Mitigation details and patches are outlined in official advisories, including NVIDIA's security bulletin at https://nvidia.custhelp.com/app/answers/detail/a_id/5816, the NVD entry at https://nvd.nist.gov/vuln/detail/CVE-2026-24175, and the CVE record at https://www.cve.org/CVERecord?id=CVE-2026-24175. Security practitioners should consult these resources for version-specific remediation guidance.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-19759
Vulnerability Data
NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause a server crash by sending a malformed request header to the server. A successful exploit of this vulnerability might lead to denial of service.
- CWE(s)
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Security engineering principles include robust exception management to keep the system in a defined state.
Fail-in-known-state reduces the impact when an uncaught exception occurs by preserving a safe condition.
Error handling requirements force structured catching and response to exceptions instead of allowing them to propagate uncaught.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices explicitly require structured exception handling to prevent uncaught exceptions from reaching production.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing can detect uncaught exceptions before production deployment.
Secure development lifecycle includes exception-handling standards that reduce uncaught exceptions.
Application security requirements typically mandate robust error and exception handling.
Secure architecture principles call for centralized, comprehensive exception management.
Secure coding standards directly require catching and handling exceptions to prevent crashes or leaks.