CVE-2025-23318 Memory corruption in Triton Inference Server
An out-of-bounds write in the Python backend allows attackers to execute code, cause denial of service, tamper with data, or disclose information.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2025-23318?
CVE-2025-23318 is a high-severity memory corruption vulnerability in Nvidia Triton Inference Server, published on 6 Aug 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure.
Which versions are affected by CVE-2025-23318?
It affects 1 product.
Products include Nvidia Triton Inference Server.
How do I fix CVE-2025-23318?
Apply the vendor's patch.
Upgrade to the fixed version. Memory-safe languages, compiler hardening and fuzzing prevent most new cases. More about Memory corruption.
Is CVE-2025-23318 being exploited?
There is no known exploitation of CVE-2025-23318 in the wild and no public exploit code.
Other vulnerabilities in Nvidia Triton Inference Server
Sources
Also known as GHSA-736h-fxpw-gmwm, MINI-4gc2-gprp-x96j.