# CVE-2026-16497: NVIDIA Triton Inference Server excessive iteration denial of service

Source: https://junglewise.ai/threats/cve-2026-16497-nvidia-triton-inference-server-excessive-iteration-denial-of  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-09-08. Updated: 2026-09-26  
License: CC BY 4.0 with a link back

CVE-2026-16497 · Severity: high · CVSS 7.5 · Published 2026-09-08

NVIDIA Triton Inference Server is a widely-used inference platform that runs machine learning models in production. A vulnerability in the Linux version allows a remote attacker to cause excessive iteration loops, leading to denial of service and unavailability of the inference service for legitimate users and applications.

Technologies: [Nvidia Triton Inference Server](https://junglewise.ai/threats/technologies/triton-inference-server). Vendors: [Nvidia](https://junglewise.ai/threats/vendors/nvidia).

## Quick answers

**Is CVE-2026-16497 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-16497 being exploited in the wild.

**How severe is CVE-2026-16497?** High severity, with a CVSS score of 7.5, published 8 September 2026.

**Which products and versions are affected?** Nvidia Triton Inference Server <UNKNOWN>.

**Is there a fix for CVE-2026-16497?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-16497 attacked?** It is attacked over the network.

**Am I affected by CVE-2026-16497?** Check whether you run Nvidia Triton Inference Server at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

The vulnerability involves a logic flaw in Triton Inference Server for Linux that permits an attacker to trigger excessive iteration in a processing loop without proper bounds checking or rate limiting. The attack is network-accessible and does not require authentication or user interaction. A successful exploit causes the server to consume CPU resources in an infinite or near-infinite loop, rendering the service unavailable. No patch details are currently available in the advisory, but NVIDIA has assigned CVE-2026-16497 and published a security bulletin.

## Affected products

- NVIDIA Triton Inference Server <UNKNOWN>

## Timeline

- 2026-09-08: disclosed

## References

- [https://github.com/NVIDIA/product-security/tree/main/2026/5875](https://github.com/NVIDIA/product-security/tree/main/2026/5875)
- [https://www.cve.org/CVERecord?id=CVE-2026-16497](https://www.cve.org/CVERecord?id=CVE-2026-16497)

## Related threats

- [NVIDIA Triton Inference Server authorization bypass](https://junglewise.ai/threats/cve-2026-47625-nvidia-triton-inference-server-authorization-bypass)
- [NVIDIA Triton Inference Server path traversal](https://junglewise.ai/threats/cve-2026-47630-nvidia-triton-inference-server-path-traversal)
- [NVIDIA Triton Inference Server improper input validation](https://junglewise.ai/threats/cve-2026-47629-nvidia-triton-inference-server-improper-input-validation)
- [NVIDIA Triton Inference Server resource exhaustion denial of service](https://junglewise.ai/threats/cve-2026-47628-nvidia-triton-inference-server-resource-exhaustion-denial-of)
- [NVIDIA Triton Inference Server path traversal](https://junglewise.ai/threats/cve-2026-47627-nvidia-triton-inference-server-path-traversal)