firstbacksecondback
51 Results
|
Poster
|
Fri 16:30 |
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection Yuxin Wang · Duanyu Feng · Yongfu Dai · Zhengyu Chen · Jimin Huang · Sophia Ananiadou · Qianqian Xie · Hao Wang |
|
|
Poster
|
Thu 16:30 |
Attack-Aware Noise Calibration for Differential Privacy Bogdan Kulynych · Juan Gomez · Georgios Kaissis · Flavio Calmon · Carmela Troncoso |
|
|
Poster
|
Wed 16:30 |
A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy Puning Zhao · Lifeng LAI · Li Shen · Qingming Li · Jiafei Wu · Zhe Liu |
|
|
Workshop
|
Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs Aly Kassem · Omar Mahmoud · Niloofar Mireshghallah · Hyunwoo Kim · Yulia Tsvetkov · Yejin Choi · Sherif Saad · Santu Rana |
||
|
Affinity Event
|
Armadillo: Robust Secure Aggregation for Federated Learning with Input Validation Yiping Ma · Yue Guo · Harish Karthikeyan · Antigoni Polychroniadou |
||
|
Affinity Event
|
Towards Privacy-Preserving Medical Imaging: Federated Learning with Differential Privacy and Secure Aggregation Using a Modified ResNet Architecture Mohamad Haj Fares · Ahmed Mohamed Saad Emam Saad |
||
|
Affinity Event
|
OPA: One-shot Private Aggregation with Single Client Interaction and its Applications to Federated Learning Harish Karthikeyan · Antigoni Polychroniadou |
||
|
Poster
|
Wed 16:30 |
Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training Kristjan Greenewald · Yuancheng Yu · Hao Wang · Kai Xu |
|
|
Workshop
|
A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage Rui Xin · Niloofar Mireshghallah · Stella Li · Michael Duan · Hyunwoo Kim · Yejin Choi · Yulia Tsvetkov · Sewoong Oh · Pang Wei Koh |
||
|
Workshop
|
A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage Rui Xin · Niloofar Mireshghallah · Stella Li · Hyunwoo Kim · Michael Duan · Yejin Choi · Yulia Tsvetkov · Sewoong Oh · Pang Wei Koh |
||
|
Workshop
|
A Cautionary Tale on the Evaluation of Differentially Private In-Context Learning Anjun Hu · Jiyang Guan · Philip Torr · Francesco Pinto |
||
|
Workshop
|
Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption Leo de Castro · Antigoni Polychroniadou · Daniel Escudero |