Zekun Xu
5 papers · 2020–2022 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🐣
Hot Topic Early Bird
🧭
Keyword Pioneer
Venues
Top co-authors
Research topics
Keywords
log loss
(2)
differential privacy
(2)
metric learning
(1)
text generation
(1)
constrained optimization
(1)
bregman divergence
(1)
nearest neighbor
(1)
privacy preserving
(1)
mahalanobis distance
(1)
binary classifier
(1)
label inference attack
(1)
privacy auditing
(1)
cross-entropy loss
(1)
information leakage
(1)
privacy leakage
(1)
membership inference
(1)
utility maximization
(1)
privacy vulnerability
(1)
cross entropy
(1)
membership inference attack
(1)
Papers
Reconstructing Test Labels from Noisy Loss Functions
AISTATS 2022
Label Inference Attacks from Log-loss Scores
ICML 2021
On a Utilitarian Approach to Privacy Preserving Text Generation
NAACL 2021
A Differentially Private Text Perturbation Method Using Regularized Mahalanobis Metric
EMNLP 2020
On Log-Loss Scores and (No) Privacy
EMNLP 2020