2024 "privacy-preserving machine learning" Papers
12 papers found
AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning
Dong Chen, Hongyuan Qu, Guangwu Xu
ICML 2024poster
Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
Yvonne Zhou, Mingyu Liang, Ivan Brugere et al.
ICML 2024posterarXiv:2402.04375
CaPS: Collaborative and Private Synthetic Data Generation from Distributed Sources
Sikha Pentyala, Mayana Pereira, Martine De Cock
ICML 2024posterarXiv:2402.08614
DataFreeShield: Defending Adversarial Attacks without Training Data
Hyeyoon Lee, Kanghyun Choi, Dain Kwon et al.
ICML 2024posterarXiv:2406.15635
Differentially Private Bias-Term Fine-tuning of Foundation Models
Zhiqi Bu, Yu-Xiang Wang, Sheng Zha et al.
ICML 2024posterarXiv:2210.00036
Ditto: Quantization-aware Secure Inference of Transformers upon MPC
Haoqi Wu, Wenjing Fang, Yancheng Zheng et al.
ICML 2024posterarXiv:2405.05525
DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)
Qiaoyue Tang, Frederick Shpilevskiy, Mathias Lécuyer
AAAI 2024paperarXiv:2312.14334
28
citations
DPZero: Private Fine-Tuning of Language Models without Backpropagation
Liang Zhang, Bingcong Li, Kiran Thekumparampil et al.
ICML 2024posterarXiv:2310.09639
Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
Florian Tramer, Gautam Kamath, Nicholas Carlini
ICML 2024poster
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
Charlie Hou, Akshat Shrivastava, Hongyuan Zhan et al.
ICML 2024posterarXiv:2406.02958
Privacy-Preserving Embedding via Look-up Table Evaluation with Fully Homomorphic Encryption
Jae-yun Kim, Saerom Park, Joohee Lee et al.
ICML 2024poster
Seesaw: Compensating for Nonlinear Reduction with Linear Computations for Private Inference
Fabing Li, Yuanhao Zhai, Shuangyu Cai et al.
ICML 2024poster