Changming Xu
5 papers · 2018–2025 · 5 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 · Silver
🏃
Academic Marathon · Sprint
Top co-authors
Research topics
Keywords
adversarial attack
(2)
robustness
(1)
neural machine translation
(1)
machine learning security
(1)
bleu score
(1)
deep neural network
(1)
adversarial perturbation
(1)
variational autoencoder
(1)
beam search
(1)
probabilistic guarantee
(1)
length normalization
(1)
coverage mechanism
(1)
wireless system vulnerability
(1)
radio frequency attack
(1)
cifar-10
(1)
probabilistic robustness bounds
(1)
certified robustness
(1)
transformations
(1)
Papers
Support is All You Need for Certified VAE Training
ICLR 2025
Cross-Input Certified Training for Universal Perturbations
ECCV 2024
Robust Universal Adversarial Perturbations
ICML 2024
Exploring Practical Vulnerabilities of Machine Learning-based Wireless Systems
NSDI 2023
A Simple and Effective Approach to Coverage-Aware Neural Machine Translation
ACL 2018