CVE-2025-46570
vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel
- State
- Published
- Severity
- 2.6 Low
- Published
- May 29, 2025
- Updated
- May 29, 2025
- Reserved
- Apr 24, 2025
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 2.6 Low | CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N | GitHub_M |
Weaknesses
- CWE-208 Observable Timing Discrepancy
Affected Products
| Product | Versions |
|---|---|
vllmvllm-project |
|
References
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.