RouteScan identifies malicious prompts in MoE LLMs using GPU expert routing telemetry as a privacy-preserving fingerprint, achieving AUROC above 0.93 on unseen harmful domains.
arXiv preprint arXiv:2602.04105 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
In shared-prefix MoE code generation, routing Jaccard similarity reaches 0.649 for identical tokens and 0.175 for different tokens, with layer-wise crossing patterns, and 67% of compiled codes fall into three assembly-equivalent groups.
citing papers explorer
-
Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork Redundancy
In shared-prefix MoE code generation, routing Jaccard similarity reaches 0.649 for identical tokens and 0.175 for different tokens, with layer-wise crossing patterns, and 67% of compiled codes fall into three assembly-equivalent groups.