Sangkyun Lee
7 papers · 2012–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (5) π Academic Marathon (14) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (14) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
IJCAI (3)
AISTATS (1)
JMLR (1)
UAI (1)
WACV (1)
Top co-authors
Keywords
representation learning
(2)
contrastive learning
(2)
model stealing
(2)
convex optimization
(1)
adversarial training
(1)
query efficiency
(1)
regularized learning
(1)
dual averaging
(1)
linear approximation
(1)
proximal algorithm
(1)
deep neural network
(1)
adversarial defense
(1)
adversarial perturbation
(1)
model explanation
(1)
saddle-point optimization
(1)
class activation map
(1)
manifold identification
(1)
interpretable ai
(1)
misdirection model
(1)
cluster-guided learning
(1)
Papers
Cluster-Guided Adversarial Perturbations for Robust Contrastive Learning
WACV 2026
Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers
UAI 2025
SwiftThief: Enhancing Query Efficiency of Model Stealing by Contrastive Learning
IJCAI 2024
Libra-CAM: An Activation-Based Attribution Based on the Linear Approximation of Deep Neural Nets and Threshold Calibration
IJCAI 2022
Model Stealing Defense against Exploiting Information Leak through the Interpretation of Deep Neural Nets
IJCAI 2022
Fast Saddle-Point Algorithm for Generalized Dantzig Selector and FDR Control with Ordered L1-Norm
AISTATS 2016
Manifold Identification in Dual Averaging for Regularized Stochastic Online Learning
JMLR 2012