漏洞信息
尽管我们使用了先进的大模型技术,但其输出仍可能包含不准确或过时的信息。神龙努力确保数据的准确性,但请您根据实际情况进行核实和判断。
Vulnerability Title
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
Vulnerability Description
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Vulnerability Type
内存缓冲区边界内操作的限制不恰当
Vulnerability Title
llama.cpp 安全漏洞
Vulnerability Description
llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp b5662之前版本存在安全漏洞,该漏洞源于GGUF模型词汇表可能触发缓冲区溢出,可能导致内存损坏和执行任意代码。
CVSS Information
N/A
Vulnerability Type
N/A