| 2026 | ACL | When Benchmarks Leak: Inference-Time Decontamination for LLMs. | Jianzhe Chai, Zhe Yu, Jun Sakuma |
| 2026 | ACL | Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG). | Junki Mori, Kazuya Kakizaki, Taiki Miyagawa, Jun Sakuma |
| 2026 | ACL | Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models. | Ragib Amin Nihal, Rui Wen, Kazuhiro Nakadai, Jun Sakuma |
| 2025 | AISTATS | Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift. | Mitsuhiro Fujikawa, Youhei Akimoto, Jun Sakuma, Kazuto Fukuchi |
| 2025 | ICCV | Disrupting Model Merging: A Parameter-Level Defense without Sacrificing Accuracy. | Junhao Wei, Yu Zhe, Jun Sakuma |
| 2025 | IJCNN | Remembering Transformer for Continual Learning. | Yuwei Sun, Ippei Fujisawa, Arthur Juliani, Jun Sakuma, Ryota Kanai |
| 2025 | IJCNN | Weakening Prediction Confidence Makes Backdoors Strengthened: A Strong Textual Backdoor Attack on Prefix-tuning. | Yixin Tan, Haoyu Zhang, Jun Sakuma |
| 2025 | MICCAI | Explainable Classifier for Malignant Lymphoma Subtyping via Cell Graph and Image Fusion. | Daiki Nishiyama, Hiroaki Miyoshi, Noriaki Hashimoto, Koichi Ohshima, Hidekata Hontani, Ichiro Takeuchi, Jun Sakuma |
| 2024 | GECCO | Linear Convergence Rate Analysis of the (1+1)-ES on Locally Strongly Convex and Lipschitz Smooth Functions. | Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto |
| 2024 | IJCNN | Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation Space. | Yuwei Sun, Hideya Ochiai, Jun Sakuma |
| 2023 | IJCAI | Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs. | Kaiwen Xu, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma |
| 2023 | WACV | Certified Defense for Content Based Image Retrieval. | Kazuya Kakizaki, Kazuto Fukuchi, Jun Sakuma |
| 2022 | AAAI | Unsupervised Causal Binary Concepts Discovery with VAE for Black-Box Model Explanation. | Thien Q. Tran, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma |
| 2022 | GECCO | Black-box min-max continuous optimization using CMA-ES with worst-case ranking approximation. | Atsuhiro Miyagi, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto |
| 2022 | IJCNN | Did You Use My GAN to Generate Fake? Post-hoc Attribution of GAN Generated Images via Latent Recovery. | Syou Hirofumi, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma |
| 2022 | IJCNN | CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy. | Daiki Nishiyama, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma |
| 2022 | IJCNN | Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning. | Rei Sato, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto |
| 2022 | IJCNN | Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis. | Yuwei Sun, Hideya Ochiai, Jun Sakuma |
| 2021 | AAAI | AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment. | Rei Sato, Jun Sakuma, Youhei Akimoto |
| 2021 | GECCO | Adaptive scenario subset selection for min-max black-box continuous optimization. | Atsuhiro Miyagi, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto |
| 2021 | GECCO | Convergence rate of the (1+1)-evolution strategy with success-based step-size adaptation on convex quadratic functions. | Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto |
| 2021 | GECCO | Level generation for angry birds with sequential VAE and latent variable evolution. | Takumi Tanabe, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto |
| 2020 | AAAI | Generate (Non-Software) Bugs to Fool Classifiers. | Hiromu Yakura, Youhei Akimoto, Jun Sakuma |
| 2020 | GECCO | Deep generative model for non-convex constraint handling. | Naoki Sakamoto, Eiji Semmatsu, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto |
| 2020 | KDD | Statistically Significant Pattern Mining with Ordinal Utility. | Thien Q. Tran, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma |
| 2019 | CCS | Robust Watermarking of Neural Network with Exponential Weighting. | Ryota Namba, Jun Sakuma |
| 2019 | IJCAI | Robust Audio Adversarial Example for a Physical Attack. | Hiromu Yakura, Jun Sakuma |
| 2019 | KDD | Seasonal-adjustment Based Feature Selection Method for Predicting Epidemic with Large-scale Search Engine Logs. | Thien Q. Tran, Jun Sakuma |
| 2018 | AAAI | Efficiently Monitoring Small Data Modification Effect for Large-Scale Learning in Changing Environment. | Hiroyuki Hanada, Atsushi Shibagaki, Jun Sakuma, Ichiro Takeuchi |
| 2018 | CCS | More Practical Privacy-Preserving Machine Learning as A Service via Efficient Secure Matrix Multiplication. | Wenjie Lu, Jun Sakuma |
| 2018 | CCS | Non-interactive and Output Expressive Private Comparison from Homomorphic Encryption. | Wenjie Lu, Jun-Jie Zhou, Jun Sakuma |
| 2018 | ISIT | Minimax Optimal Additive Functional Estimation with Discrete Distribution: Slow Divergence Speed Case. | Kazuto Fukuchi, Jun Sakuma |
| 2018 | TrustCom | Outsourced Private Function Evaluation with Privacy Policy Enforcement. | Noboru Kunihiro, Wenjie Lu, Takashi Nishide, Jun Sakuma |
| 2017 | CCS | Mis-operation Resistant Searchable Homomorphic Encryption. | Keita Emura, Takuya Hayashi, Noboru Kunihiro, Jun Sakuma |
| 2017 | CCS | Privacy-preserving and Optimal Interval Release for Disease Susceptibility. | Kosuke Kusano, Ichiro Takeuchi, Jun Sakuma |
| 2017 | CCS | Malware Analysis of Imaged Binary Samples by Convolutional Neural Network with Attention Mechanism. | Hiromu Yakura, Shinnosuke Shinozaki, Reon Nishimura, Yoshihiro Oyama, Jun Sakuma |
| 2017 | DEXA | Towards Privacy-Preserving Record Linkage with Record-Wise Linkage Policy. | Takahito Kaiho, Wenjie Lu, Toshiyuki Amagasa, Jun Sakuma |
| 2017 | DIS | Differentially Private Empirical Risk Minimization with Input Perturbation. | Kazuto Fukuchi, Quang-Khai Tran, Jun Sakuma |
| 2017 | ICML | Differentially Private Chi-squared Test by Unit Circle Mechanism. | Kazuya Kakizaki, Kazuto Fukuchi, Jun Sakuma |
| 2017 | ISIT | Minimax optimal estimators for additive scalar functionals of discrete distributions. | Kazuto Fukuchi, Jun Sakuma |
| 2017 | NDSS | Using Fully Homomorphic Encryption for Statistical Analysis of Categorical, Ordinal and Numerical Data. | Wenjie Lu, Shohei Kawasaki, Jun Sakuma |
| 2017 | SmartComp | Differentially Private Semi-Supervised Classification. | Xu Long, Jun Sakuma |
| 2016 | ACML | Secure Approximation Guarantee for Cryptographically Private Empirical Risk Minimization. | Toshiyuki Takada, Hiroyuki Hanada, Yoshiji Yamada, Jun Sakuma, Ichiro Takeuchi |
| 2016 | AINA | Ice and Fire: Quantifying the Risk of Re-identification and Utility in Data Anonymization. | Hiroaki Kikuchi, Takayasu Yamaguchi, Koki Hamada, Yuji Yamaoka, Hidenobu Oguri, Jun Sakuma |
| 2016 | ESORICS | A Study from the Data Anonymization Competition Pwscup 2015. | Hiroaki Kikuchi, Takayasu Yamaguchi, Koki Hamada, Yuji Yamaoka, Hidenobu Oguri, Jun Sakuma |
| 2016 | ISITA | Fairy ring: Ubiquitous secure multiparty computation framework for smartphone applications. | Tadanori Teruya, Yoshiki Aoki, Jun Sakuma |
| 2015 | SP | Privacy-Preserving Statistical Analysis by Exact Logistic Regression. | David A. duVerle, Shohei Kawasaki, Yoshiji Yamada, Jun Sakuma, Koji Tsuda |
| 2015 | SP | Efficient Secure Outsourcing of Genome-Wide Association Studies. | Wenjie Lu, Yoshiji Yamada, Jun Sakuma |
| 2014 | AINA | Privacy-Preserving Hypothesis Testing for the Analysis of Epidemiological Medical Data. | Hiroaki Kikuchi, Tomoki Sato, Jun Sakuma |
| 2014 | IDEAS | A scheme for privacy-preserving ontology mapping. | Toshiyuki Amagasa, Fan Zhang, Jun Sakuma, Hiroyuki Kitagawa |
| 2014 | RecSys | Correcting Popularity Bias by Enhancing Recommendation Neutrality. | Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, Jun Sakuma |
| 2013 | DBSEC | Bloom Filter Bootstrap: Privacy-Preserving Estimation of the Size of an Intersection. | Hiroaki Kikuchi, Jun Sakuma |
| 2013 | ICDM | The Independence of Fairness-Aware Classifiers. | Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, Jun Sakuma |
| 2013 | RecSys | Efficiency Improvement of Neutrality-Enhanced Recommendation. | Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, Jun Sakuma |
| 2012 | ICDM | Considerations on Fairness-Aware Data Mining. | Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, Jun Sakuma |
| 2012 | RecSys | Enhancement of the Neutrality in Recommendation. | Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, Jun Sakuma |
| 2012 | SMC | Applicability of existing anonymization methods to large location history data in urban travel. | Rie Shigetomi Yamaguchi, Keiichi Hirota, Koki Hamada, Katsumi Takahashi, Kazutaka Matsuzaki, Jun Sakuma, Yasuyuki Shirai |
| 2011 | ICDM | Fairness-aware Learning through Regularization Approach. | Toshihiro Kamishima, Shotaro Akaho, Jun Sakuma |
| 2010 | ICML | Online Prediction with Privacy. | Jun Sakuma, Hiromi Arai |
| 2010 | KDD | Collusion-resistant privacy-preserving data mining. | Bin Yang, Hiroshi Nakagawa, Issei Sato, Jun Sakuma |
| 2009 | ACML | Privacy-Preserving Evaluation of Generalization Error and Its Application to Model and Attribute Selection. | Jun Sakuma, Rebecca N. Wright |
| 2009 | CEC | A new real-coded genetic algorithm using the adaptive selection network for detecting multiple optima. | Dan Oshima, Atsushi Miyamae, Jun Sakuma, Shigenobu Kobayashi, Isao Ono |
| 2009 | GECCO | Adaptation of expansion rate for real-coded crossovers. | Youhei Akimoto, Jun Sakuma, Isao Ono, Shigenobu Kobayashi |
| 2009 | SIGIR | Link analysis for private weighted graphs. | Jun Sakuma, Shigenobu Kobayashi |
| 2008 | GECCO | Functionally specialized CMA-ES: a modification of CMA-ES based on the specialization of the functions of covariance matrix adaptation and step size adaptation. | Youhei Akimoto, Jun Sakuma, Isao Ono, Shigenobu Kobayashi |
| 2008 | ICML | Privacy-preserving reinforcement learning. | Jun Sakuma, Shigenobu Kobayashi, Rebecca N. Wright |
| 2008 | PAKDD | Large-Scale k-Means Clustering with User-Centric Privacy Preservation. | Jun Sakuma, Shigenobu Kobayashi |
| 2008 | PPSN | Functional-Specialization Multi-Objective Real-Coded Genetic Algorithm: FS-MOGA. | Naoki Hamada, Jun Sakuma, Shigenobu Kobayashi, Isao Ono |
| 2007 | EMO | Constraint-Handling Method for Multi-objective Function Optimization: Pareto Descent Repair Operator. | Ken Harada, Jun Sakuma, Isao Ono, Shigenobu Kobayashi |
| 2007 | GECCO | Uniform sampling of local pareto-optimal solution curves by pareto path following and its applications in multi-objective GA. | Ken Harada, Jun Sakuma, Shigenobu Kobayashi, Isao Ono |
| 2007 | GECCO | A genetic algorithm for privacy preserving combinatorial optimization. | Jun Sakuma, Shigenobu Kobayashi |
| 2006 | CEC | Instance-Based Policy Search using Binomial Distribution Crossover and Iterated Refreshment. | Chikao Tsuchiya, Kokolo Ikeda, Jun Sakuma, Isao Ono, Shigenobu Kobayashi |
| 2006 | GECCO | Local search for multiobjective function optimization: pareto descent method. | Ken Harada, Jun Sakuma, Shigenobu Kobayashi |
| 2006 | SMC | An Evolutionary Algorithm for Optimizing Functions with UV Structures. | Hiroshi Takeichi, Isao Ono, Jun Sakuma, Shigenobu Kobayashi |
| 2005 | GECCO | Adaptive isolation model using data clustering for multimodal function optimization. | Shin Ando, Jun Sakuma, Shigenobu Kobayashi |
| 2005 | GECCO | Real-coded crossover as a role of kernel density estimation. | Jun Sakuma, Shigenobu Kobayashi |
| 2005 | GECCO | Latent variable crossover for k-tablet structures and its application to lens design problems. | Jun Sakuma, Shigenobu Kobayashi |
| 2005 | ICDE | Fast Approximate Similarity Search in Extremely High-Dimensional Data Sets. | Michael E. Houle, Jun Sakuma |
| 2002 | GECCO | k-tablet Structures and Crossover on Latent Variables for Real-Coded GA. | Jun Sakuma, Shigenobu Kobayashi |
| 2001 | CEC | Extrapolation-directed crossover for real-coded GA: overcoming deceptive phenomena by extrapolative search. | Jun Sakuma, Shigenobu Kobayashi |
| 2000 | GECCO | Extrapolation-Directed Crossover for Job-shop Scheduling Problems: Complementary Combination with JOX. | Jun Sakuma, Shigenobu Kobayashi |