Jun Sakuma
14 papers · 2016–2026 · 10 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Gold π Academic Marathon Β· Half π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (35)
ποΈ
Keyword Collector
(75)
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Renaissance Researcher
(6)
Venues
Top co-authors
Research topics
Machine Learning
(10)
Artificial Intelligence
(7)
Core AI
(7)
Application Areas
(5)
Deep Learning
(4)
Learning Types Β· Machine Learning
(4)
Optimization & Theory
(4)
Learning Types Β· Deep Learning
(3)
Computer Vision
(2)
Security & Privacy
(2)
Analysis
(2)
Computer Science
(1)
Mathematics & Optimization
(1)
Reinforcement Learning
(1)
Applications
(1)
Keywords
physical attack
(2)
adversarial example
(2)
differential privacy
(1)
image classification
(1)
robust optimization
(1)
adversarial robustness
(1)
false discovery rate
(1)
neural architecture search
(1)
sim-to-real transfer
(1)
transfer learning
(1)
feature extraction
(1)
logistic regression
(1)
model misspecification
(1)
gradient-based optimization
(1)
speech recognition
(1)
concept-based explanation
(1)
model merging
(1)
robust reinforcement learning
(1)
empirical risk minimization
(1)
causal inference
(1)
Papers
When Benchmarks Leak: Inference-Time Decontamination for LLMs
ACL 2026
Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy
ICCV 2025
Explainable Classifier for Malignant Lymphoma Subtyping via Cell Graph and Image Fusion
MICCAI 2025
Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift
AISTATS 2025
Certified Defense for Content Based Image Retrieval
WACV 2023
Demographic Parity Constrained Minimax Optimal Regression under Linear Model
NeurIPS 2023
Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs
IJCAI 2023
Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification
NeurIPS 2022
Unsupervised Causal Binary Concepts Discovery with VAE for Black-Box Model Explanation
AAAI 2022
AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment
AAAI 2021
Generate (Non-Software) Bugs to Fool Classifiers
AAAI 2020
Robust Audio Adversarial Example for a Physical Attack
IJCAI 2019
Differentially Private Chi-squared Test by Unit Circle Mechanism
ICML 2017
Secure Approximation Guarantee for Cryptographically Private Empirical Risk Minimization
ACML 2016