A hybrid ASIC+eFPGA architecture is proposed to add adaptive security mechanisms to edge LLM inference while retaining ASIC efficiency.
Phantom:{Privacy-Preserving}deep neural network model obfuscation in heterogeneous{TEE}and{GPU}system,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Secure eFPGA-Enabled Edge LLM Inference: Architectural and Hardware Countermeasures
A hybrid ASIC+eFPGA architecture is proposed to add adaptive security mechanisms to edge LLM inference while retaining ASIC efficiency.