Topic
3 articles
CyberSecureToday covers GPU Cluster across 3 articles published between 1 Oct 2026 and 10 Oct 2026.
The coverage includes 3 vulnerability advisories. 3 advisories are rated critical or high severity.
Stories on GPU Cluster most often intersect with Frontier AI, Remote Code Execution and vLLM, with Technology, Cloud & SaaS the most affected sector. The most recent story, “vLLM Distributed KV-Cache Memory Deserialization Flaw Enables Arbitrary Model Weight Extraction”, was published 10 Oct 2026. Every article is listed below, newest first, with the affected products, severity and remediation guidance in each piece.
Threat IntelA high-severity deserialization vulnerability in vLLM's distributed PagedAttention KV-cache transfer protocol allows attackers to compromise GPU worker nodes.
Agentic AIA critical flaw in Mooncake distributed KVCache transfer engine allows unauthenticated TCP attackers to read and write arbitrary process memory, exposing LLM prompt caches.
Threat IntelAn unauthenticated RPyC service in LightLLM visual_only deployments enables remote attackers to execute arbitrary code on GPU clusters via pickle deserialization.