Author

Ke Cheng

h-index 6 View on Semantic Scholar

We have 5 of 29 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access 2026

Privacy-Preserving Graph Neural Network Inference Using Homomorphic Encryption for Secure Graph Classification

Graph Neural Networks have achieved remarkable success in graph-based learning tasks, but often require access to sensitive data during inference, raising privacy concerns in domains such as healthcare, finance, and cybersecurity. Homomorphic Encryption enables computation on encrypted data; however, directly applying...

S. ur Rahman, Zhao Chang, Ke Cheng · Journal of networking and ne... · 0 citations

Preprint Aug 2026

Noise-Aware Shrinkage for Differentially Private Zeroth-Order Fine-Tuning of Large Language Models

SAGE is proposed, a noise-aware shrinkage method that adaptively attenuates privatized estimates according to their estimated signal quality, and shows that shrinkage reduces the quadratic update-risk term faster than the linear descent term, preserving useful descent while limiting the influence of noise-dominated upd...

Le-Le Zheng, Wei-Feng Kong, Xinyi Zhang et al. · 0 citations

Preprint Aug 2026

From Bilinear to Linear: Differentially Private Federated LoRA via Low-Dimensional Parameterization

FedHSIP reformulates all LoRA parameters into a shared low-dimensional trainable vector, enabling clients to optimize and communicate only low-dimensional updates, and transforms federated LoRA from a bilinear factor aggregation problem into a unified linear parameter space, thereby eliminating aggregation mismatch and...

Le-Le Zheng, Rui Hu, Tao Zhang et al. · 0 citations

Preprint Aug 2026

When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy

Experiments on vision and language tasks across multiple privacy budgets show that DP-Merging consistently improves private merged-model performance while preserving the privacy guarantees of the underlying DP fine-tuning procedures.

Jin Liu, Jun-Kang Liu, Ning Xi et al. · 0 citations

Preprint Aug 2026

FedGSA: Geometry-Consistent Subspace Aggregation for Differentially Private Federated LoRA

FedGSA, a geometry-consistent aggregation framework for differentially private federated LoRA, is proposed and it is proved that FedGSA incurs no additional privacy loss beyond client-side DP training and establishes its convergence under standard assumptions.

Le-Le Zheng, Rui Hu, Tao Zhang et al. · 0 citations