-
CVE-2026-24183 and CVE-2026-24184: About NVIDIA Cumulus Linux (24th Aug 2026)
Preface: About 26 years ago, mainframe computers—especially the IBM S/390—installed FICON switches with optical fiber connections to interconnect with host nodes. As time went by, the design of supercomputers relied more heavily on Linux-based HPC (High-Performance Computing) clusters. Nvidia’s CUDA tools empowered traditional 64-bit instruction sets (which favor sequential processing) to extend into GPU multiprocessing…
-
The evolution sequence of vulnerabilities in the NVIDIA Triton inference server (CVE-2026-47629, CVE-2026-47627, CVE-2026-47628 and CVE-2026-47606). 20th Aug 2026
Preface: NVIDIA Dynamo-Triton and Triton inference server are functionally identical; NVIDIA Dynamo-Triton is simply the new name for the Triton inference server. NVIDIA has integrated Triton into its broader Dynamo platform and officially renamed it Dynamo-Triton. Thousands of enterprises and technology brands worldwide use NVIDIA Triton inference servers (now integrated into NVIDIA Dynamo-Triton) to run…
-
AMD ID- AMD-SB 7062: About Efficient Symbolic Execution design weakness (18th Aug 2026)
The security bulletin was published by AMD on August 12, 2026. Preface: Linux was introduced to High-Performance Computing (HPC) in the late 1990s, fundamentally transforming how we build powerful machines. Before this shift, traditional supercomputers were dominated by proprietary systems from vendors like Cray, IBM, and Bull. These legacy systems relied on specialized vector processors…
-
Brief Description of Scheduler-Contention Side Channel on AMD “Zen” Processors (17th Aug 2026)
Initial publication 2026-08-12 (Official) Preface: This article provides a brief overview of the AMD-SB-7069 security bulletin, focusing on scheduler contention-side channel behavior on AMD “Zen” processors and how we handle it in our code. Background: To facilitate understanding of the infographic, the following is a detailed explanation. If you look at the top left, Block…
-
CVE-2026-68820: Use after free in Windows Ancillary Function Driver for WinSock (14th Aug 2026)
Preface: Any standard machine learning framework running on Windows (such as PyTorch, TensorFlow, or ML.NET) interacts indirectly with afd.sys when performing network tasks (such as downloading datasets, communicating with distributed nodes, or querying cloud APIs). Background: afd[.]sys is the Windows Accessibility driver for WinSock. It is a core kernel-mode driver in the Windows operating system,…
-
Third-party opinions on CVE-2026-6727 (non-AMD), associated with AMD ID: AMD-SB-7064 (13th Aug 2026)
Preface: The AMD EPYC 9004 and 9005 series processors heavily demand—and absolutely dominate—the High-Performance Computing (HPC) and AI markets. Because CPUs and GPUs have fundamentally different processing architectures, there is no single “1-to-1” equivalence. Instead, the number of AMD EPYC 9005 (Zen 5 “Turin”) processors needed to equal one NVIDIA H100 GPU depends entirely on…
-
About AMD-SB 3032: Extracting VM Secrets through Power Side Channels on AMD SEV-ES and SEV-SNP (12th Aug 2026)
Preface: AMD EPYC processors include RAPL (Running Average Power Limit) functionality, which provides a standardized cross-vendor interface for enterprise data centers. Enterprise Linux ecosystems rely heavily on built-in diagnostic and orchestration frameworks. By exposing counters through the RAPL standard via the Linux PowerCap and perf subsystems, server administrators can monitoring AMD hardware. Background: AMD Secure…
-
Detailed description of the AMD-SB-7061 Safe RET interrupt vulnerability.
This article was published on 10th Aug 2026 Official release date: August 4, 2026 Preface: AMD Zen 4 architecture is widely used in high-performance computing (HPC). It powers 4th Generation AMD EPYC server processors (such as Genoa, Genoa-X with 3D V-Cache) and the AMD Instinct MI300A accelerated processing unit (APU), which combine Zen 4 CPU…
-
CVE-2026-47487: NVIDIA Triton Inference Server for Linux contains a vulnerability (CWE-22)
This article was published on 10th Aug 2026 Official release date: August 4, 2026 Preface: The NVIDIA Triton Inference Server was developed to solve a critical bottleneck in the AI lifecycle: the messy, fragmented gap between AI model training and production deployment. Historically, companies faced massive engineering overhead when attempting to push their completed models…
-
CVE-2026-24254: A core out-of-bounds write vulnerability specific to the Multimodal Serving Topology within NVIDIA Dynamo for Linux. (7th Aug 2026)
Remark: The article was originally scheduled for publication on August 7, 2026. Due to personal arrangements, I will release the analysis details ahead of schedule. Preface: To understand why NVIDIA Dynamo for Linux is a critical piece of infrastructure, you have to look at how the AI industry has fundamentally shifted from running single-model queries…