CVE-2026-34760

Affects: large language model, vLLM

CVSS: MEDIUM · 5.9 v3.1
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L
Published: 2026-04-02
Weakness: CWE-20
Source: nvd.nist.gov/vuln/detail/CVE-2026-34760

Description

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results in inconsistency between audio heard by humans (e.g., through headphones/regular speakers) and audio processed by AI models (Which infra via Librosa, such as vllm, transformer). This issue has been patched in version 0.18.0.

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-2026-34760 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