CVE-2025-46560
LLaMA LLM Multimodal Tokenizer Resource Exhaustion
Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to inefficient list concatenation operations, the algorithm exhibits quadratic time complexity (O(n²)), allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5.
INFO
Published Date :
April 30, 2025, 1:15 a.m.
Last Modified :
April 30, 2025, 2:15 p.m.
Source :
[email protected]
Remotely Exploitable :
Yes !
Impact Score :
3.6
Exploitability Score :
2.8
Affected Products
The following products are affected by CVE-2025-46560
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2025-46560.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2025-46560 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2025-46560 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Apr. 30, 2025
Action Type Old Value New Value Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg -
New CVE Received by [email protected]
Apr. 30, 2025
Action Type Old Value New Value Added Description vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to inefficient list concatenation operations, the algorithm exhibits quadratic time complexity (O(n²)), allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5. Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Added CWE CWE-1333 Added Reference https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py#L1182-L1197 Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2025-46560 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2025-46560
weaknesses.