Roei Schuster
4 papers · 2020–2023 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🐣
Hot Topic Early Bird
🧭
Keyword Pioneer
Venues
Top co-authors
Research topics
Artificial Intelligence
(3)
Core AI
(3)
Machine Learning
(2)
Natural Language Processing
(2)
Application Areas
(2)
Resources & Methods
(2)
Computer Science
(1)
Deep Learning
(1)
Security & Privacy
(1)
Applications
(1)
Architectures
(1)
Differential Privacy
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Keywords
differential privacy
(1)
representation learning
(1)
ensemble learning
(1)
attention mechanism
(1)
pattern learning
(1)
adversarial attack
(1)
privacy leakage
(1)
hidden representation
(1)
language generation
(1)
side-channel attack
(1)
transformer language model
(1)
feed-forward layer
(1)
nucleus sampling
(1)
transformer model
(1)
neural network
(1)
key-value memory
(1)
memorization recall
(1)
vote histogram
(1)
text de-anonymization
(1)
privacy leak
(1)
Papers
Understanding Transformer Memorization Recall Through Idioms
EACL 2023
In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning
NeurIPS 2022
Transformer Feed-Forward Layers Are Key-Value Memories
EMNLP 2021
De-Anonymizing Text by Fingerprinting Language Generation
NeurIPS 2020