Memory LeakWeakness · CWE-401

CVE-2026-47482

HIGH · 7.5 CVSS v3.1 Published 2026-07-14
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
84/100
Remediation priority · High
Remotely reachable No privileges Zero-click 5 weeks old

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause missing release of memory after effective lifetime. A successful exploit of this vulnerability might lead to denial of service.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · moderate confidence

NVIDIA Triton Inference Server for Linux has a memory leak vulnerability where memory is not properly released after its effective lifetime. An attacker can exploit this to cause memory exhaustion, leading to denial of service. The vulnerability stems from missing deallocation calls in specific code paths.

MitigationApply the vendor patch when available; in the interim, implement resource limits and monitor memory usage to mitigate DoS risk. Ensure proper memory management practices are followed in custom extensions or models.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify Triton Inference Server version
    Run 'tritonserver --version' or check the Docker image tag if using containers. On Linux systems, also check via 'dpkg -l | grep triton' or 'pip show triton-inference-server' if installed via pip.
    Affected if The installed version falls within the vulnerable version range and has not been patched.
  2. Confirm Linux environment
    Verify the OS is Linux using 'uname -a' or 'cat /etc/os-release'. The CVE specifically affects the Linux platform.
    Affected if Running Triton Inference Server on Linux and the version is unpatched.
  3. Monitor memory consumption
    Use 'ps aux | grep tritonserver' to locate the process, then monitor its RSS memory with 'ps -o rss=' or via 'top' / 'htop' over time. Track memory growth trend over several hours under normal workload.
    Affected if Memory usage grows continuously without stabilization, indicating a memory leak.
  4. Check for model loading activity
    Review Triton logs for model load/unload operations using 'cat /var/log/triton/*.log' or container logs via 'docker logs'. The vulnerability stems from missing deallocation in specific code paths related to model lifecycle.
    Affected if Frequent model loading/unloading operations are performed and memory usage increases with each cycle.

If running an unpatched version of Triton Inference Server on Linux with observable continuous memory growth during normal operation or model loading cycles, the environment is likely affected by this memory leak vulnerability.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

From vendor data
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Apply the vendor patch when available; in the interim, implement resource limits and monitor memory usage to mitigate DoS risk. Ensure proper memory management practices are followed in custom extensions or models.

Have this fixed Scoped from the published advisory
  • Consultation2.0 h
  • Implementation8.0 h
  • Testing4.0 h
  • Review / QA2.0 h
16.0 hours of engineering $2,800
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,480.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-47482 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-47482 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data