Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2025-46560— vLLM phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service

Quick assessment

Affected
vllm-project vllm
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.8.0至0.8.5之前版本存在安全漏洞，该漏洞源于输入预处理逻辑效率低下，可能导致资源耗尽。

CVSS 6.5 · Medium EPSS 0.52% · P43

Possible ATT&CK Techniques 1 AI

T1496 · Resource Hijacking
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2025-46560

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
CWE-1333
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.8.0至0.8.5之前版本存在安全漏洞，该漏洞源于输入预处理逻辑效率低下，可能导致资源耗尽。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
vllm-project vllm >= 0.8.0, < 0.8.5 -

II. Public POCs for CVE-2025-46560

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2025-46560

请登录查看更多情报信息。

Patches & Fixes for CVE-2025-46560 (1)

Vendor Advisories for CVE-2025-46560 (1)

Same Patch Batch · vllm-project · 2025-04-30 · 3 CVEs total

CVE-2025-32444 10.0 CRITICAL vLLM Vulnerable to Remote Code Execution via Mooncake Integration
CVE-2025-30202 7.5 HIGH Data exposure via ZeroMQ on multi-node vLLM deployment

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-1333

V. Comments for CVE-2025-46560

No comments yet

Leave a comment