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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
UJEM-KL improves cross-model transferability of untargeted jailbreaks on VLMs by maximizing entropy at decision tokens rather than enforcing fixed response patterns.
citing papers explorer
-
RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry
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.
-
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
UJEM-KL improves cross-model transferability of untargeted jailbreaks on VLMs by maximizing entropy at decision tokens rather than enforcing fixed response patterns.