Marika Swanberg
4 papers · 2021–2025 · 3 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(12)
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
differential privacy
(3)
multi-task learning
(1)
distribution learning
(1)
language model
(1)
privacy-utility trade-off
(1)
label inference attack
(1)
privacy auditing
(1)
reconstruction advantage
(1)
privatization mechanism
(1)
training data
(1)
sampling algorithm
(1)
total variation distance
(1)
label inference
(1)
inference attack
(1)
data memorization
(1)
model personalization
(1)
reconstruction attack
(1)
threat model
(1)
worst-case generalization
(1)
label privatization
(1)
Papers
Measuring memorization in language models via probabilistic extraction
NAACL 2025
Privacy in Metalearning and Multitask Learning: Modeling and Separations
AISTATS 2025
Auditing Privacy Mechanisms via Label Inference Attacks
NeurIPS 2024
Differentially Private Sampling from Distributions
NeurIPS 2021