ActInv reconstructs client inputs from server-visible activations in LLM split inference despite common defenses, PAF quantifies per-layer leakage risk, and PriPert improves defenses via calibrated perturbations.
Title resolution pending
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
-
What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference
ActInv reconstructs client inputs from server-visible activations in LLM split inference despite common defenses, PAF quantifies per-layer leakage risk, and PriPert improves defenses via calibrated perturbations.