{"data":{"id":"6b8c7ce4-e853-4975-9bf2-65dc6067a1fe","title":"PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models","summary":"PGuard is a native, streaming guardrail that runs inside a multimodal LLM's backbone rather than as an external serving dependency. It uses dynamic layer gating over residual-stream representations to detect safety-relevant signals per token during prefill and decoding. It adds only 0.82-2.26% end-to-end overhead on Qwen3.5-122B-A10B served by SGLang, and on text queries with Qwen3.5-9B it reaches an average F1 of 0.836 across more than 30 benchmarks.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://arxiv.org/abs/2611.02791v2","publishedAt":"2026-11-02T09:03:39.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Qwen3.5-122B-A10B","Qwen3.5-9B","SGLang"],"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":"2026-11-02T09:03:39.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}