Shengyuan Hu
5 papers · 2019–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌈 Renaissance Researcher (5) 🌍 Conference Polyglot (3) 🏃 Academic Marathon (6) 🐝 Cross-Pollinator (15) 🌉 Interdisciplinary Bridge
🧭
Keyword Pioneer
❓
The Questioner
Conferences
NIPS (3)
ICLR (1)
ICML (1)
Top co-authors
Research topics
Keywords
adversarial attack
(2)
federated learning
(2)
multi-task learning
(1)
data poisoning
(1)
anomaly detection
(1)
computer vision
(1)
adversarial perturbation
(1)
watermark detection
(1)
model poisoning
(1)
cross-silo federated learning
(1)
gradient method
(1)
adversarial image
(1)
llm watermarking
(1)
content authentication
(1)
differential privacy
(1)
Papers
Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
ICLR 2025
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
NIPS 2024
On Privacy and Personalization in Cross-Silo Federated Learning
NIPS 2022
Ditto: Fair and Robust Federated Learning Through Personalization
ICML 2021
A New Defense Against Adversarial Images: Turning a Weakness into a Strength
NIPS 2019