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.
arXiv preprint arXiv:2409.19134 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
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.
-
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.