PrivCode++ introduces the first DP code generation method protecting both prompts and code via latent-conditioned two-stage training, claiming higher utility and stronger privacy than prior baselines.
arXiv preprint arXiv:2512.07342 , 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
DP-SAPF uses gradient-magnitude saliency after noise addition to select LoRA targets for DP fine-tuning of public models, reporting improved synthetic image utility and fidelity on four datasets with lower compute.
citing papers explorer
-
PrivCode++: Latent-Conditioned Differentially Private Code Generation for Comprehensive Guarantees
PrivCode++ introduces the first DP code generation method protecting both prompts and code via latent-conditioned two-stage training, claiming higher utility and stronger privacy than prior baselines.
-
DP-SAPF: Saliency-Aware Parameter Fine-tuning of Public Models for Differentially Private Image Synthesis
DP-SAPF uses gradient-magnitude saliency after noise addition to select LoRA targets for DP fine-tuning of public models, reporting improved synthetic image utility and fidelity on four datasets with lower compute.