CVE-2025-25183
Published: 07 February 2025
Summary
CVE-2025-25183 is a low-severity Improper Validation of Integrity Check Value (CWE-354) vulnerability in Vllm Vllm. Its CVSS base score is 2.6 (Low).
Operationally, ranked in the top 44.2% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as NLP and Transformers; in the Adversarial Attacks risk domain.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-4074
Vulnerability details
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's…
more
built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions. The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use. This issue has been addressed in version 0.7.2 and all users are advised to upgrade. There are no known workarounds for this vulnerability.
- 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
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Proper validation of integrity check values is required for reliable tamper detection, directly reducing undetected modification risks.
Requires validation of integrity check values on every resolution response, directly mitigating tampered or corrupted DNS data.
Control mandates proper validation of integrity values (checksums) on prepared data, making flawed validation of those checks ineffective for attackers.
Requires use of proper integrity verification tools, reducing the chance an incorrect check value is accepted.
Requires proper validation of integrity mechanisms, directly mitigating flawed check-value handling.