CVE-2025-23320 Information disclosure in Triton Inference Server
An attacker can cause shared memory limit exhaustion via large requests, leading to information disclosure in NVIDIA Triton Inference Server.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2025-23320?
CVE-2025-23320 is a high-severity 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 the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might lead to information disclosure.
Weakness: CWE-209
Which versions are affected by CVE-2025-23320?
It affects 1 product.
Products include Nvidia Triton Inference Server.
How do I fix CVE-2025-23320?
Apply the vendor's patch.
Is CVE-2025-23320 being exploited?
There is no known exploitation of CVE-2025-23320 in the wild and no public exploit code.
Public exploit code: 1 proofs of concept on GitHub.
Other vulnerabilities in Nvidia Triton Inference Server
Sources
Also known as GHSA-r4v6-683m-mqm9, MINI-mq8p-w8hm-p7gf.