Browse / Unbounded Consumption / CVE-2024-8939
vLLM Denial of Service via the best_of parameter
- Class
- Unbounded Consumption (filed by a model that read the advisory)
- Technique
- Denial of service
- Affected
- vllm (PyPI)
- CVSS
- CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- EPSS
- 0.2% chance of exploitation in 30 days
How it works, in short
Very large best_of values in vLLM completion requests consume excessive resources without timeouts, leaving the API unresponsive to other users. (Our summary, written by a model. The source text is below.)
Details
A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.
References
- https://nvd.nist.gov/vuln/detail/CVE-2024-8939
- https://github.com/vllm-project/vllm/issues/6137
- https://access.redhat.com/security/cve/CVE-2024-8939
- https://bugzilla.redhat.com/show_bug.cgi?id=2312782
- https://github.com/vllm-project/vllm
Source: GitHub Advisory Database, used under CC BY 4.0.