CVE-2025-46560
Vllm 0.8.0 – 0.8.5
Raw vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:HSummary
CVE-2025-46560 is a medium-severity Inefficient Regular Expression Complexity (CWE-1333) vulnerability in Vllm Vllm. Its CVSS base score is 6.5 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique Endpoint Denial of Service (T1499); ranked at the 39th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as NLP and Transformers; in the Adversarial Attacks risk domain.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SA-15 (Development Process, Standards, and Tools) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
vLLM is a high-throughput inference and serving engine for large language models. Versions 0.8.0 through 0.8.4 contain a performance vulnerability in the multimodal tokenizer's input preprocessing logic. The affected code replaces placeholder tokens such as <|audio_|> and <|image_|> by repeatedly concatenating tokens according to precomputed lengths; the use of inefficient list operations produces quadratic time complexity, enabling an attacker to supply specially crafted inputs that trigger excessive CPU and memory consumption.
An authenticated remote attacker with low privileges can submit malicious multimodal prompts to the inference engine. Because the vulnerability affects only availability, successful exploitation results in resource exhaustion that can degrade or deny service to other users without disclosing data or altering model behavior.
The issue is resolved in vLLM 0.8.5. The project security advisory GHSA-vc6m-hm49-g9qg and the corresponding code change in phi4mm.py document the patch that replaces the quadratic concatenation pattern with an efficient implementation.
The vulnerability is specific to multimodal LLM workloads and carries a CVSS score of 6.5 with a high availability impact. EPSS remains low, with a recorded peak of 0.0152.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-12671
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- NLP and Transformers
- Risk Domain
- Adversarial Attacks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: llms, vllm
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation can discover inefficient regex patterns via performance or static analysis.
Development standards and tools can require safe regex construction and forbid known exponential patterns.
Denial-of-service protections limit resource exhaustion caused by expensive regex evaluation.
Input validation can constrain data that would otherwise trigger worst-case regex complexity.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing can detect and reject regex patterns with exponential worst-case complexity.
Secure development lifecycle mandates review of algorithmic efficiency, directly addressing ReDoS-prone regex.
Application security requirements can specify input-validation rules that limit regex complexity.
Secure architecture principles encourage avoidance of computationally expensive constructs such as catastrophic backtracking.
Secure coding standards explicitly prohibit or limit the use of inefficient regular expressions.