Shaokui Wei
10 papers
· 2022–2025
· 4 conferences
· across top CS/AI conferences
Achievements
π
Conference Polyglot
(4)
π§
Keyword Pioneer
πΊοΈ
Taxonomy Completionist
(18)
π
Interdisciplinary Bridge
π
Cross-Pollinator
(13)
π
Renaissance Researcher
(6)
π
Century Club
(10)
Conferences
NIPS (5)
ICCV (2)
ICLR (2)
AISTATS (1)
Top co-authors
Research topics
Keywords
backdoor defense
(6)
backdoor attack
(5)
neural network
(2)
model security
(2)
model unlearning
(2)
sharpness-aware minimization
(1)
deep learning
(1)
constrained optimization
(1)
reproducing kernel hilbert space
(1)
machine learning security
(1)
adversarial defense
(1)
poisoning attack
(1)
gradient norm
(1)
bi-level optimization
(1)
neural network robustness
(1)
adversarial example
(1)
model utility
(1)
fairness constraint
(1)
model purification
(1)
backdoor mitigation
(1)