Topic

GPU Clusters: news, advisories and analysis

3 articlesUpdated 7 Oct 2026

CyberSecureToday covers GPU Clusters across 3 articles published between 15 Sep 2026 and 7 Oct 2026. The coverage includes 3 vulnerability advisories. 3 advisories are rated critical or high severity, and 1 involves a flaw listed in CISA's Known Exploited Vulnerabilities catalog.

Stories on GPU Clusters most often intersect with vLLM, AI Security and Large Language Models, with Technology, Cloud & SaaS the most affected sector. The most recent story, “vLLM Flaw Lets Unauthenticated Attackers Poison KV Caches and Hijack Model Outputs”, was published 7 Oct 2026. Every article is listed below, newest first, with the affected products, severity and remediation guidance in each piece.

Latest coverage

ThreatsCloud & SaaSCritical
vLLM Flaw Lets Unauthenticated Attackers Poison KV Caches and Hijack Model Outputs
A critical flaw in vLLM distributed inference engine (CVE-2026-43109) allows unauthenticated network actors to poison PagedAttention KV caches and hijack model outputs.
Aisha Noor7 Oct 20268 min read
ThreatsCloud & SaaSHigh
vLLM EngineCore Guided Decoding State Failure Triggers Multi-Tenant GPU Cluster Denial of Service (GHSA-85xf-c7hm-whqw)
A high-severity flaw in vLLM EngineCore guided decoding allows crafted JSON Schema requests to trigger non-recoverable state crashes across multi-tenant GPU workers.
Mei-Lin Chen30 Sep 202610 min read
ThreatsCloud & SaaSCritical
Ray Distributed AI Framework Code Injection Flaw Exploited to Compromise AI Clusters
CISA issues an emergency directive on CVE-2025-62593, warning that unauthenticated code injection in Ray AI distributed computing clusters allows adversaries to seize GPU clusters and training models.
Daniel Okafor15 Sep 20268 min read

Latest coverage

vLLM Flaw Lets Unauthenticated Attackers Poison KV Caches and Hijack Model Outputs

vLLM EngineCore Guided Decoding State Failure Triggers Multi-Tenant GPU Cluster Denial of Service (GHSA-85xf-c7hm-whqw)

Ray Distributed AI Framework Code Injection Flaw Exploited to Compromise AI Clusters