Shengyuan Hu
5 papers · 2019–2025 · 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(5)
Application Areas
(5)
Artificial Intelligence
(4)
Core AI · Artificial Intelligence
(2)
Learning Paradigms · Artificial Intelligence
(2)
Computer Vision
(1)
Deep Learning
(1)
Security & Privacy
(1)
Analysis
(1)
Core AI · Computer Vision
(1)
Learning Paradigms · Machine Learning
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Privacy
(1)
Keywords
adversarial attack
(3)
federated learning
(2)
multi-task learning
(1)
data poisoning
(1)
anomaly detection
(1)
computer vision
(1)
machine unlearning
(1)
adversarial perturbation
(1)
watermark detection
(1)
model poisoning
(1)
cross-silo federated learning
(1)
gradient method
(1)
knowledge memorization
(1)
adversarial image
(1)
large language model
(1)
model privacy
(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
NeurIPS 2024
On Privacy and Personalization in Cross-Silo Federated Learning
NeurIPS 2022
Ditto: Fair and Robust Federated Learning Through Personalization
ICML 2021
A New Defense Against Adversarial Images: Turning a Weakness into a Strength
NeurIPS 2019