Bug 2344292 (CVE-2025-25183, GHSA-rm76-4mrf-v9r8)

Summary:	CVE-2025-25183 vllm: vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
Product:	[Other] Security Response	Reporter:	OSIDB Bzimport <bzimport>
Component:	vulnerability	Assignee:	Product Security DevOps Team <prodsec-dev>
Status:	NEW ---	QA Contact:
Severity:	low	Docs Contact:
Priority:	low
Version:	unspecified	CC:	jeder
Target Milestone:	---	Keywords:	Security
Target Release:	---
Hardware:	All
OS:	Linux
Whiteboard:
Fixed In Version:		Doc Type:	If docs needed, set a value
Doc Text:	A flaw was found in the vllm package. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. The impact of a collision would be using a cache that was generated using different content. With the knowledge of the prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use.	Story Points:	---
Clone Of:		Environment:
Last Closed:		Type:	---
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2025-02-06 22:01:57 UTC

### Summary

Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior.

### Details

Prefix caching makes use of Python's 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.

### Impact

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.

### Solution

We address this problem by initializing hashes in vllm with a value that is no longer constant and predictable. It will be different each time vllm runs. This restores behavior we got in Python versions prior to 3.12.

Using a hashing algorithm that is less prone to collision (like sha256, for example) would be the best way to avoid the possibility of a collision. However, it would have an impact to both performance and memory footprint. Hash collisions may still occur, though they are no longer straight forward to predict.

To give an idea of the likelihood of a collision, for randomly generated hash values (assuming the hash generation built into Python is uniformly distributed), with a cache capacity of 50,000 messages and an average prompt length of 300, a collision will occur on average once every 1 trillion requests.

### References

* https://github.com/vllm-project/vllm/pull/12621
* https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7
* https://github.com/python/cpython/pull/99541