Shuyu Cheng
7 papers · 2019–2026 · 6 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 Silver
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
๐
Grand Slam
Top co-authors
Research topics
Keywords
adversarial attack
(4)
query efficiency
(4)
gradient estimation
(4)
hard-label attack
(2)
transfer learning
(2)
surrogate model
(2)
bayesian optimization
(1)
black-box attack
(1)
adversarial perturbation
(1)
variational autoencoder
(1)
zeroth-order optimization
(1)
gradient-free optimization
(1)
wasserstein gradient flow
(1)
black-box adversarial attack
(1)
transfer ability
(1)
transfer-based attack
(1)
neural density estimator
(1)
transfer-based prior
(1)
ray search optimization
(1)
black-box optimization
(1)
Papers
Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks
AAAI 2026
Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors
ICLR 2025
Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
ICML 2024
On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms
NeurIPS 2021
A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models
AISTATS 2020
Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded Manifolds
ECCV 2020
Improving Black-box Adversarial Attacks with a Transfer-based Prior
NeurIPS 2019