Wojciech Czaja
5 papers · 2021–2023 · 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
data poisoning
(2)
federated learning
(2)
semi-supervised learning
(1)
image synthesis
(1)
conditional generation
(1)
adversarial attack
(1)
language model
(1)
hinge loss
(1)
poisoning attack
(1)
generative adversarial network
(1)
gradient attack
(1)
evasion attack
(1)
adversarial example
(1)
gradient inversion
(1)
data reconstruction
(1)
classifier training
(1)
gradient matching
(1)
threat model
(1)
adversarial poisoning
(1)
clean-label attack
(1)
Papers
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
ICLR 2023
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models
ICLR 2022
Adversarial Examples Make Strong Poisons
NeurIPS 2021
A Multi-Class Hinge Loss for Conditional GANs
WACV 2021
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
ICLR 2021