3 papers
cs.CV2022
PGADA: Perturbation-Guided Adversarial Alignment for Few-shot Learning Under the Support-Query Shift
Siyang Jiang, Wei Ding, Hsi-Wen Chen +1
Few-shot learning methods aim to embed the data to a low-dimensional embedding space and then classify the unseen query data to the seen support set. While these works assume that…
cs.CR2018
Privacy and Utility Tradeoff in Approximate Differential Privacy
Quan Geng, Wei Ding, Ruiqi Guo +1
We characterize the minimum noise amplitude and power for noise-adding mechanisms in -differential privacy for single real-valued query function. We derive new lower bounds…
cs.CR2018
Optimal Noise-Adding Mechanism in Additive Differential Privacy
Quan Geng, Wei Ding, Ruiqi Guo +1
We derive the optimal -differentially private query-output independent noise-adding mechanism for single real-valued query function under a general cost-minimization framew…