8 matches found
CVE-2026-50144
A flaw was found in ncnn, a high-performance neural network inference framework. A remote attacker could craft a malicious model file that, when processed by a user, triggers an out-of-bounds heap write. This vulnerability in the ncnn::ParamDict::loadparam function is caused by insufficient...
CVE-2026-50144
ncnn (mobile-optimized neural network framework) contains an out-of-bounds heap write in ParamDict::load_param() when loading a malicious .param model, caused by a negative parameter id indexing before params[NCNN_MAX_PARAM_COUNT]. This is exploitable via Net::load_param() and is fixed by commit ...
CVE-2026-50144 ncnn: Out-of-bounds heap write in ParamDict::load_param via unchecked negative parameter id
ncnn is a high-performance neural network inference framework optimized for the mobile platform. In commit e54f7b1f88434e1d844ea0551b880a1cfb079ce1 and earlier, ncnn allows an out-of-bounds heap write in ncnn::ParamDict::loadparam when Net::loadparam loads a malicious .param model file because th...
CVE-2026-50144 ncnn: Out-of-bounds heap write in ParamDict::load_param via unchecked negative parameter id
ncnn is a high-performance neural network inference framework optimized for the mobile platform. In commit e54f7b1f88434e1d844ea0551b880a1cfb079ce1 and earlier, ncnn allows an out-of-bounds heap write in ncnn::ParamDict::loadparam when Net::loadparam loads a malicious .param model file because th...
UBUNTU-CVE-2026-21869
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the ndiscard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fill...
PT-2026-2109
Name of the Vulnerable Software and Affected Versions llama.cpp versions prior to commit 55d4206c9 Description llama.cpp is an inference engine for several Large Language Models LLMs implemented in C/C++. The software parses the n discard parameter directly from JSON input in its completion...
SUSE CVE-2024-50610
GSL GNU Scientific Library through 2.8 has an integer signedness error in gslsimansolvemany in siman/siman.c. When params.ntries is negative, incorrect memory allocation occurs...
The vulnerability of the tif_getimage.c component in the LibTIFF library, related to writing beyond the buffer boundaries, allows an attacker to access confidential data, compromise its integrity, and cause service failures.
The vulnerability of the tifgetimage.c component in the LibTIFF library is related to a buffer overflow vulnerability. This could potentially lead to a buffer overflow through the creation of an RGBA image, due to the presence of the “Nagative-size-param” condition. Exploiting this vulnerability...