5 papers
PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
Murat Bilgehan Ertan, Xiaochen Zhu, Phuong Ha Nguyen +2
We introduce PACZero, a family of PAC-private zeroth-order mechanisms for fine-tuning large language models that delivers usable utility at . This privacy regime…
SIMD-PAC-DB: Pretty Performant PAC Privacy
Ilaria Battiston, Dandan Yuan, Xiaochen Zhu +1
This work presents a highly optimized implementation of PAC-DB, a recent and promising database privacy model. We prove that our SIMD-PAC-DB can compute the same privatized answer…
Private Prediction via PAC Privacy
Xiaochen Zhu, Mayuri Sridhar, Srinivas Devadas
Machine learning models are increasingly served behind APIs. This renders private prediction, i.e., privatizing a model's outputs rather than its parameters, a natural privacy targ…
Passive Inference Attacks on Split Learning via Adversarial Regularization
Xiaochen Zhu, Xinjian Luo, Yuncheng Wu +3
Split Learning (SL) has emerged as a practical and efficient alternative to traditional federated learning. While previous attempts to attack SL have often relied on overly strong…
Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation
Xiaochen Zhu, Vincent Y. F. Tan, Xiaokui Xiao
Graph neural networks (GNNs) have gained an increasing amount of popularity due to their superior capability in learning node embeddings for various graph inference tasks, but trai…