ONE 输入验证错误漏洞

ONE is a high-performance edge-side neural network inference framework developed by Samsung. Versions prior to ONE 1.30.0 contained a vulnerability related to input validation errors. This vulnerability stemmed from integer overflows during the calculation of tensor size allocation, which could...

SUSE CVE-2026-34159

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserializetensor skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPHCOMPUTE messages. Combined...

DEBIAN-CVE-2026-34159

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserializetensor skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPHCOMPUTE messages. Combined...

CVE-2026-34159

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserializetensor skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPHCOMPUTE messages. Combined...

llama.cpp 缓冲区错误漏洞

Llama.cpp is a multimodal model developed by Georgi Gerganov. Prior versions of llama.cpp b8492 contained a buffer error vulnerability. This vulnerability stemmed from the deserializetensor function in the RPC backend, which skipped all boundary verifications when the buffer field of the tensor w...

PT-2026-29570

Name of the Vulnerable Software and Affected Versions llama.cpp versions prior to b8492 Description A logic bug in the RPC backend's deserialize tensor function allows an unauthenticated attacker to read and write arbitrary process memory. This occurs because bounds validation is skipped when a...

Heap-based Buffer Overflow

Overview Affected versions of this package are vulnerable to Heap-based Buffer Overflow in the ggmlnbytes function. An attacker can achieve memory corruption and potentially execute arbitrary code by supplying a specially crafted GGUF file with manipulated tensor dimensions that trigger an intege...

CVE-2026-33298

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

UBUNTU-CVE-2026-33298

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

CVE-2026-33298

Summary (CVE-2026-33298) : llama.cpp (C/C++) contains an integer overflow in the ggml_nbytes function during GGUF tensor parsing, allowing an attacker to bypass memory validation by crafting tensor dimensions. This can cause ggml_nbytes to report a far too small size (examples cite 4 MB vs exabyt...

CVE-2026-33298 llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

CVE-2026-33298

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

CVE-2026-33298 llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

CVE-2026-33298 llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the ggmlnbytes function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes ggmlnbytes to return a significantly smaller...

PT-2026-27272

Name of the Vulnerable Software and Affected Versions llama.cpp versions prior to b7824 Description The software is susceptible to an integer overflow in the ggml nbytes function. This allows an attacker to bypass memory validation by creating a specially crafted GGUF file with specific tensor...

Deep Learning-Driven Friendly Jamming for Secure Multicarrier ISAC under Channel Uncertainty

Integrated sensing and communication ISAC systems promise efficient spectrum utilization by jointly supporting radar sensing and wireless communication. This paper presents a deep learning-driven framework for enhancing physical-layer security in multicarrier ISAC systems under imperfect channel...

Kraken: Higher-Order EM Side-Channel Attacks on DNNs in near and Far Field

The multi-million dollar investment required for modern machine learning ML has made large ML models a prime target for theft. In response, the field of model stealing has emerged. Attacks based on physical side-channel information have shown that DNN model extraction is feasible, even on CUDA...

Neurosymbolic Learning for Advanced Persistent Threat Detection under Extreme Class Imbalance

The growing deployment of Internet of Things IoT devices in smart cities and industrial environments increases vulnerability to stealthy, multi-stage advanced persistent threats APTs that exploit wireless communication. Detection is challenging due to severe class imbalance in network traffic,...

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models

Jailbreaking large language models LLMs has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts to elicit restricted or unsafe outputs, a phenomenon commonly referred to as...

Ex-Google Engineer Convicted for Stealing AI Secrets for China Startup

A former Google engineer accused of stealing thousands of the company's confidential documents to build a startup in China has been convicted in the U.S., the Department of Justice DoJ announced Thursday. Linwei Ding aka Leon Ding, 38, was convicted by a federal jury on seven counts of economic...