conftrace_
← Authors

Wojciech Czaja

5 papers · 2021–2023 · 3 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
🌍 Conference Polyglot (3) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15)

Conferences

ICLR (3) NIPS (1) WACV (1)

Top co-authors

Tom Goldstein (4) Jonas Geiping (4) Micah Goldblum (3) Liam H Fowl (3) W. Ronny Huang (1) Michael Moeller (1) Rama Chellappa (1) Ping-yeh Chiang (1) Ilya Kavalerov (1) Liam Fowl (1)

Keywords

semi-supervised learning (1) data poisoning (1) image synthesis (1) conditional generation (1) hinge loss (1) poisoning attack (1) generative adversarial network (1) evasion attack (1) adversarial example (1) classifier training (1) adversarial poisoning (1) secure dataset release (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 NIPS 2021 Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching ICLR 2021 A Multi-Class Hinge Loss for Conditional GANs WACV 2021