CVE-2024-8939

Affects: vLLM

CVSS
MEDIUM · 6.2v3.1
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Published
2024-09-17
Weakness
CWE-400
Source
nvd.nist.gov/vuln/detail/CVE-2024-8939

Description

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

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2024-8939 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming