Liam H Fowl
4 papers · 2021–2023 · 1 venue · 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 ↓
🌉
Interdisciplinary Bridge · Bronze
Venues
Top co-authors
Research topics
Keywords
federated learning
(3)
language model
(2)
privacy attack
(2)
adversarial attack
(1)
gradient attack
(1)
gradient inversion
(1)
data reconstruction
(1)
gradient matching
(1)
threat model
(1)
clean-label attack
(1)
model integrity
(1)
data aggregation
(1)
targeted poisoning
(1)
targeted extraction
(1)
data poisoning
(1)
gradient updates
(1)
Papers
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
ICLR 2023
Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation
ICLR 2023
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models
ICLR 2022
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
ICLR 2021