Bo-Han Kung
4 papers · 2021–2025 · 4 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)
Top co-authors
Research topics
Machine Learning
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Core AI
(3)
Learning Types · Machine Learning
(3)
Application Areas
(2)
Optimization & Theory · Machine Learning
(2)
Computer Vision
(1)
Analysis
(1)
Architectures
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
object detection
(2)
certified robustness
(2)
formal verification
(1)
adversarial attack
(1)
image manifold
(1)
randomized smoothing
(1)
adversarial perturbation
(1)
generative adversarial network
(1)
class weighting
(1)
universal adversarial perturbation
(1)
class-weighted loss
(1)
physical adversarial attack
(1)
adversarial patch
(1)
neural network
(1)
annealing mechanism
(1)
quasiconvex optimization
(1)
input-specific algorithm
(1)
certified radius
(1)
lipschitz neural network
(1)
block reflector orthogonal layer
(1)
Papers
Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
ICML 2025
Towards Large Certified Radius in Randomized Smoothing Using Quasiconcave Optimization
AAAI 2024
Class-Aware Robust Adversarial Training for Object Detection
CVPR 2021
Naturalistic Physical Adversarial Patch for Object Detectors
ICCV 2021