Sungmin Han

5 papers · 2022–2026 · 3 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 · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

IJCAI (3) UAI (1) WACV (1)

Top co-authors

Sangkyun Lee (5) Jeonghyun Lee (4) Seongyun Seo (1)

Research topics

Machine Learning (4) Deep Learning (3) Artificial Intelligence (2) Architectures (2) Core AI (2) Learning Types · Machine Learning (2) Natural Language Processing (1) Application Areas (1) Applications (1) Core Methods (1) Learning Types · Deep Learning (1) Optimization & Theory (1)

Keywords

representation learning (2) contrastive learning (2) model stealing (2) adversarial training (1) query efficiency (1) linear approximation (1) deep neural network (1) adversarial defense (1) adversarial perturbation (1) model explanation (1) reference activation (1) class activation map (1) interpretability method (1) interpretable ai (1) misdirection model (1) cluster-guided learning (1) information leak (1) transformer-based text classifier (1) activation attribution (1) token-level attribution (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