CVE-2026-53923

A flaw was found in vLLM. Integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels leads to partial tensor processing. This results in the output tensor retaining previously used GPU memory, which, in multi-tenant inference deployments, can expose sensitive tensor data from other...

PT-2026-50472

Name of the Vulnerable Software and Affected Versions vLLM versions 0.5.5 through 0.23.1rc0 Description Integer truncation of tensor dimensions in GGUF dequantize kernels within csrc/quantization/gguf/gguf kernel.cu leads to partial tensor processing. The output tensor is allocated at full size...

EUVD-2026-24616

Integer overflow in buffer size calculation could result in out of bounds memory access when handling large tensors in Samsung Open Source ONE. Affected version is prior to commit 1.30.0...

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...

Important: Red Hat Security Advisory: Red Hat AI Inference Server 3.2.5 (TPU)

Red Hat AI Inference Server 3.2.5 TPU is now available. Red Hat® AI Inference Server...

lsmmdma (>=0.0.4 <=0.1.7), tpu-tf2 (=1.0.0) potentially affected by CVE-2022-23568 via tensorflow-cpu (=2.7.0)

tensorflow-cpu PYPI version =2.7.0 is affected by a known vulnerability. The following packages have a transitive dependency on tensorflow-cpu and may be impacted: - lsmmdma =0.0.4, =0.1.7 - tpu-tf2 =1.0.0 Source cves: CVE-2022-23568 Source advisory: OSV:GHSA-6445-FM66-FVQ2...