126 matches found
MINI-WVPF-RH8F-G3RR
Bulletin has no description...
MINI-RVX2-542X-8H4H
Bulletin has no description...
MINI-G4CV-R6PF-35MQ
Bulletin has no description...
MINI-2MW8-876P-RM68
Bulletin has no description...
MINI-M8Q6-MFP9-CPHP
Bulletin has no description...
MINI-M8VH-8W2F-6R2J
Bulletin has no description...
MINI-M4VF-67MH-RXH8
Bulletin has no description...
MINI-GQ35-RX9M-X369
Bulletin has no description...
MINI-46X7-R642-VM2V
Bulletin has no description...
MINI-M8WV-M872-WCCQ
Bulletin has no description...
MINI-W2CV-645X-8587
Bulletin has no description...
MINI-45R2-VV2M-F6V6
Bulletin has no description...
MINI-835Q-9CV3-99H3
Bulletin has no description...
MINI-94FC-2HQX-WMP5
Bulletin has no description...
MINI-CQM3-JJX3-V6RQ
Bulletin has no description...
CGA-RX9X-25F6-MVC3
Bulletin has no description...
MINI-3FFM-M726-X3RP
Bulletin has no description...
GPUBreach: Privilege Escalation Attacks on GPUs Using Rowhammer
NVIDIA GPUs with GDDR memories have been shown susceptible to Rowhammer-based bit-flips, similar to CPUs. However, Rowhammer exploits on GPUs have been limited to injecting untargeted bit-flips in victim data like weights of machine learning models, to degrade model accuracy, unlike CPU exploits...
CVE-2026-42079
PPTAgent (the PPTAgent framework) is affected by CVE-2026-42079 due to an arbitrary code execution flaw: Python eval() executes LLM-generated code with builtins in scope. This vulnerability existed prior to commit 418491a and has been patched in that commit. The issue is triggered locally (attack...
Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed as a privacy boundary, we reveal that compromised model code is sufficient to steal them. Current passive...