Skip to main content

Observable Discrepancy

CVE-2025-46570

Low
2.6/10

Summary

The package vLLM is an inference and serving engine for large language models (LLMs). In versions prior to 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.

  • HIGH
  • NETWORK
  • NONE
  • UNCHANGED
  • REQUIRED
  • LOW
  • LOW
  • NONE

CWE-203 - Observable Discrepancy

The product behaves differently or sends different responses under different circumstances in a way that is observable to an unauthorized actor, which exposes security-relevant information about the state of the product, such as whether a particular operation was successful or not.

References

Advisory Timeline

  • Published