Mengda Yang
4 papers · 2022–2025 · 2 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
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
data reconstruction attack
(2)
privacy attack
(1)
privacy preservation
(1)
query efficiency
(1)
feature representation
(1)
black-box attack
(1)
collaborative inference
(1)
generative adversarial network
(1)
model inversion attack
(1)
privacy leakage
(1)
split learning
(1)
long-tailed learning
(1)
reconstruction attack
(1)
latent space search
(1)
split inference
(1)
feature-oriented reconstruction
(1)
model partitioning
(1)
sensitive feature distillation
(1)
model compression
(1)
feature-level transfer learning
(1)
Papers
From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning
CVPR 2025
A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning
CVPR 2024
GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference
NeurIPS 2023
Measuring Data Reconstruction Defenses in Collaborative Inference Systems
NeurIPS 2022