CVE-2025-46570
LOWDescription
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.
CVSS v3.1 Score
Weakness Type (CWE)
Affected Products
| Vendor | Product |
|---|---|
| vllm | vllm |
References
Frequently Asked Questions
What is CVE-2025-46570? +
How severe is CVE-2025-46570? +
What products are affected by CVE-2025-46570? +
How do I check if I'm vulnerable to CVE-2025-46570? +
Related Vulnerabilities
Padding oracle attack vulnerability in Oberon microsystem AG’s ocrypto library in all versions since 3.1.0 and prior to 3.9.2 allows …
SCRAM (Salted Challenge Response Authentication Mechanism) is part of the family of Simple Authentication and Security Layer (SASL, RFC 4422) …
Quiet is an alternative to team chat apps like Slack, Discord, and Element that does not require trusting a central …
SignXML is an implementation of the W3C XML Signature standard in Python. When verifying signatures with X509 certificate validation turned …
Padding oracle attack vulnerability in Oberon microsystem AG’s Oberon PSA Crypto library in all versions since 1.0.0 and prior to …
An observable timing discrepancy in the ASP could allow a privileged attacker to perform a brute-force attack against the hash …