{"data":{"id":"1ed4558f-7a32-4ad4-9711-91f0108e1968","title":"KVGuard: A KV Cache Safety Checker for LLM Serving Systems","summary":"KVGuard is a memory-safety checker for the KV cache in LLM serving systems, which use PagedAttention to map requests onto fixed-size physical blocks through a CPU-built block table. It performs five safety checks across the PagedAttention workflow, using compact per-block shadow metadata, and catches the boundary where a violation is introduced. A prototype on vLLM and SGLang covers all 29 historical KV cache safety bugs from the two systems' patch histories, finds 8 previously unknown violations with no false positives, adds 3.0% and 7.4% geomean TPOT overhead on Qwen 2.5 14B, and uses at most 0.11% of KV cache memory.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.06138v1","publishedAt":"2026-11-04T08:22:37.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["vLLM","SGLang","Qwen 2.5 14B"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-04T08:22:37.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality","integrity"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}