LoREnc secures foundation models and adapters by truncating dominant low-rank components and compensating only in authorized adapters, causing unauthorized outputs to collapse while authorized performance remains exact.
High-resolution image synthesis with latent diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SCDiff adds a parametric spatial weighting module and dual similarity-diversity loss to diffusion-based text-to-image models to increase visual novelty while preserving semantic alignment.
citing papers explorer
-
LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
LoREnc secures foundation models and adapters by truncating dominant low-rank components and compensating only in authorized adapters, causing unauthorized outputs to collapse while authorized performance remains exact.
-
Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weighting
SCDiff adds a parametric spatial weighting module and dual similarity-diversity loss to diffusion-based text-to-image models to increase visual novelty while preserving semantic alignment.