CVE-2025-46560: vLLM phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
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.
Classification
CVE ID: CVE-2025-46560
CVSS Base Severity: MEDIUM
CVSS Base Score: 6.5
CVSS Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Problem Types
CWE-1333: Inefficient Regular Expression ComplexityAffected Products
Vendor: vllm-project
Product: vllm
Exploit Prediction Scoring System (EPSS)
EPSS Score: 0.05% (probability of being exploited)
EPSS Percentile: 14.14% (scored less or equal to compared to others)
EPSS Date: 2025-05-29 (when was this score calculated)
Stakeholder-Specific Vulnerability Categorization (SSVC)
SSVC Exploitation: poc
SSVC Technical Impact: partial
SSVC Automatable: false
References
https://nvd.nist.gov/vuln/detail/CVE-2025-46560https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg
https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py#L1182-L1197