CVE-2024-42478

Affects: llama.cpp

CVSS: MEDIUM · 5.3v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Published: 2024-08-12
Weakness: CWE-125, CWE-125
Source: nvd.nist.gov/vuln/detail/CVE-2024-42478

Description

llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary address reading. This vulnerability is fixed in b3561.

References

https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-5vm9-p64x-gqw9

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2024-42478 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

CVE-2026-34159(CRITICAL)
CVE-2026-33298(HIGH)
CVE-2026-27940(HIGH)
CVE-2026-21869(HIGH)
CVE-2025-52566(HIGH)
CVE-2025-49847(HIGH)
CVE-2024-42477(MEDIUM)
CVE-2024-42479(CRITICAL)

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