Publications

Recent Preprint

  • Kazuto Fukuchi, Ryuichiro Hataya, and Kota Matsui. Provable Data Scaling Law for Meta Learning via Complexity Minimization. arXiv:2606.02008v1 [stat.ML], 2026. arXiv
  • Shojiro Yamabe, Kazuto Fukuchi, and Jun Sakuma. Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation. arXiv:2406.03862v3 [cs.LG], 2026. arXiv
  • Kazuto Fukuchi, Ryuichiro Hataya, and Kota Matsui. Provable Target Sample Complexity Improvements as Pre-Trained Models Scale. arXiv:2602.04233v1 [stat.ML], 2026. arXiv
  • Kazuto Fukuchi. Meta Optimality for Demographic Parity Constrained Regression via Post-Processing. arXiv:2506.13947v1 [stat.ML], 2025. arXiv

Recent Paper

  • Maaya Sakata and Kazuto Fukuchi. Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-off. Proceedings of the 43nd International Conference on Machine Learning, 2026. To appear. Spotlight presentation.
  • Kazuto Fukuchi, Ryuichiro Hataya, and Kota Matsui. Provable Target Sample Complexity Improvements as Pre‑Trained Models Scale. Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, 2026. to appear. arXiv
  • Shojiro Yamabe, Kazuto Fukuchi, and Jun Sakuma. Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation. The Fourteenth International Conference on Learning Representations, 10 pages, 2026. arXiv
  • Kazuto Fukuchi. Meta Optimality for Demographic Parity Constrained Regression via Post-Processing. Proceedings of the 42nd International Conference on Machine Learning, vol. 267, pp. 18024-18046, 2025. arXiv Virtual Link
  • Mitsuhiro Fujikawa, Youhei Akimoto, Jun Sakuma, and Kazuto Fukuchi. Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, vol. 258, pp. 392-410, 2025. arXiv Poster Link
  • Kazuya Kakizaki, Kazuto Fukuchi, and Jun Sakuma. Deterministic and Probabilistic Certified Defenses for Content-Based Image Retrieval. IEICE Transactions on Information and Systems, vol. E108.D, 1, pp. 92-109, 2025. doi: 10.1587/transinf.2023EDP7229.

Journal

  • Kazuya Kakizaki, Kazuto Fukuchi, and Jun Sakuma. Deterministic and Probabilistic Certified Defenses for Content-Based Image Retrieval. IEICE Transactions on Information and Systems, vol. E108.D, 1, pp. 92-109, 2025. doi: 10.1587/transinf.2023EDP7229.
  • Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Convergence Rate of the (1+1)-ES on Locally Strongly Convex and Lipschitz Smooth Functions. IEEE Transactions on Evolutionary Computation, vol. 28, 2, pp. 501-515, 2024. doi: 10.1109/TEVC.2023.3266955.
  • Atsuhiro Miyagi, Yoshiki Miyauchi, Atsuo Maki, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Covariance Matrix Adaptation Evolutionary Strategy with Worst-Case Ranking Approximation for Min–Max Optimization and Its Application to Berthing Control Tasks. ACM Transactions on Evolutionary Learning and Optimization, vol. 3, 2, 2023. doi: 10.1145/3603716. arXiv
  • Daiki Nishiyama, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy. IEICE Transactions on Information and Systems, vol. E106-d, 4, pp. 523-537, 2023. doi: 10.1587/transinf.2022EDP7200.
  • Atsuhiro Miyagi, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Adaptive scenario subset selection for worst-case optimization and its application to well placement optimization. Applied Soft Computing, vol. 133, 109842, pp. 1-19, 2022. doi: 10.1016/j.asoc.2022.109842. arXiv
  • Jiayang Liu, Weiming Zhang, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Unauthorized AI cannot recognize me: Reversible adversarial example. Pattern Recognition, vol. 134, 109048, pp. 1-9, 2022. doi: 10.1016/j.patcog.2022.109048.
  • Thien Quan Tran, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Statistically Significant Pattern Mining with Ordinal Utility. IEEE Transactions on Knowledge and Data Engineering, vol. 35, 9, pp. 8770-8783, 2022. doi: 10.1109/tkde.2022.3208626.
  • Yu Zhe, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Domain Generalization via Adversarially Learned Novel Domains. IEEE Access, vol. 10, pp. 101855-101868, 2022. doi: 10.1109/access.2022.3209815.
  • Kazuto Fukuchi, Chia-Mu Yu, and Jun Sakuma. Locally Differentially Private Minimum Finding. IEICE Transactions on Information and Systems, vol. E105-d, 8, pp. 1418-1430, 2022. doi: 10.1587/transinf.2021EDP7187. arXiv
  • Kazuto Fukuchi, Toshihiro Kamishima, and Jun Sakuma. Prediction with Model-Based Neutrality. IEICE Transactions on Information and Systems, vol. E98.d, 8, pp. 1503-1516, 2015. doi: 10.1587/transinf.2014EDP7367.

Conference

  • Maaya Sakata and Kazuto Fukuchi. Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-off. Proceedings of the 43nd International Conference on Machine Learning, 2026. To appear. Spotlight presentation.
  • Kazuto Fukuchi, Ryuichiro Hataya, and Kota Matsui. Provable Target Sample Complexity Improvements as Pre‑Trained Models Scale. Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, 2026. to appear. arXiv
  • Shojiro Yamabe, Kazuto Fukuchi, and Jun Sakuma. Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation. The Fourteenth International Conference on Learning Representations, 10 pages, 2026. arXiv
  • Kazuto Fukuchi. Meta Optimality for Demographic Parity Constrained Regression via Post-Processing. Proceedings of the 42nd International Conference on Machine Learning, vol. 267, pp. 18024-18046, 2025. arXiv Virtual Link
  • Mitsuhiro Fujikawa, Youhei Akimoto, Jun Sakuma, and Kazuto Fukuchi. Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, vol. 258, pp. 392-410, 2025. arXiv Poster Link
  • Kazuto Fukuchi and Jun Sakuma. Demographic Parity Constrained Minimax Optimal Regression under Linear Model. Advances in Neural Information Processing Systems, vol. 36, pp. 8653-8689, 2023. arXiv Poster
  • Kaiwen Xu, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, pp. 519-526, 2023. doi: 10.24963/ijcai.2023/58.
  • Yoshimasa Akimoto, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Privformer: Privacy-preserving Transformer with MPC. 2023 IEEE 8th European Symposium on Security and Privacy, pp. 392-410, 2023. doi: 10.1109/EuroSP57164.2023.00031.
  • Kazuya Kakizaki, Kazuto Fukuchi, and Jun Sakuma. Certified Defense for Content Based Image Retrieval. The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 4561-4570, 2023.
  • Takumi Tanabe, Rei Sato, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification. Advances in Neural Information Processing Systems, vol. 35, 6967–6981 pages, 2022. arXiv
  • Atsuhiro Miyagi, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Black-box min-max continuous optimization using CMA-ES with worst-case ranking approximation. GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 823-831, 2022. doi: 10.1145/3512290.3528702.
  • Daiki Nishiyama, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy. 2022 International Joint Conference on Neural Networks (IJCNN), 1–8 pages, 2022. doi: 10.1109/ijcnn55064.2022.9892108.
  • Rei Sato, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning. 2022 International Joint Conference on Neural Networks (IJCNN), 1–10 pages, 2022. doi: 10.1109/ijcnn55064.2022.9892464.
  • Hirofumi Syou, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Did You Use My GAN to Generate Fake? Post-hoc Attribution of GAN Generated Images via Latent Recovery. 2022 International Joint Conference on Neural Networks (IJCNN), 1–8 pages, 2022. doi: 10.1109/ijcnn55064.2022.9892704.
  • Yu Zhe, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Domain Generalization via Adversarial Learned Novel Domains. 2022 IEEE International Conference on Multimedia and Expo (ICME), 1–6 pages, 2022. doi: 10.1109/icme52920.2022.9860025.
  • Thien Quan Tran, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation. The Thirty-Sixth AAAI Conference on Artificial Intelligence, vol. 36, 9, pp. 9614-9622, 2022. doi: 10.1609/aaai.v36i9.21195. arXiv
  • Atsuhiro Miyagi, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Adaptive scenario subset selection for min-max black-box continuous optimization. GECCO '21: Genetic and Evolutionary Computation Conference, 697–705 pages, 2021. doi: 10.1145/3449639.3459291.
  • Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions. GECCO '21: Genetic and Evolutionary Computation Conference, 2021. doi: 10.1145/3449639.3459289. arXiv
  • Takumi Tanabe, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Level generation for angry birds with sequential VAE and latent variable evolution. GECCO '21: Genetic and Evolutionary Computation Conference, 1052–1060 pages, 2021. doi: 10.1145/3449639.3459290.
  • Thien Quan Tran, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Statistically Significant Pattern Mining with Ordinal Utility. The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 1645–1655 pages, 2020. doi: 10.1145/3394486.3403215. arXiv
  • Naoki Sakamoto, Eiji Semmatsu, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Deep generative model for non-convex constraint handling. GECCO '20: Genetic and Evolutionary Computation Conference, 636–644 pages, 2020. doi: 10.1145/3377930.3390170.
  • Kazuto Fukuchi, Satoshi Hara, and Takanori Maehara. Faking Fairness via Stealthily Biased Sampling. AAAI Conference on Artificial Intelligence, vol. 34, pp. 412-419, 2020. doi: 10.1609/aaai.v34i01.5377. arXiv Slides
  • Kazuto Fukuchi and Jun Sakuma. Minimax Optimal Additive Functional Estimation with Discrete Distribution: Slow Divergence Speed Case. 2018 IEEE International Symposium on Information Theory (ISIT), pp. 1041-1045, 2018. doi: 10.1109/isit.2018.8437725. arXiv
  • Kazuto Fukuchi, Quan Khai Tran, and Jun Sakuma. Differentially Private Empirical Risk Minimization with Input Perturbation. Discovery Science, pp. 82-90, 2017. arXiv
  • Kazuya Kakizaki, Kazuto Fukuchi, and Jun Sakuma. Differentially Private Chi-squared Test by Unit Circle Mechanism. The 34th International Conference on Machine Learning, vol. 70, 1761–1770 pages, 2017.
  • Kazuto Fukuchi and Jun Sakuma. Minimax Optimal Estimators for Additive Scalar Functionals of Discrete Distributions. 2017 IEEE International Symposium on Information Theory (ISIT), pp. 2103-2107, 2017. doi: 10.1109/ISIT.2017.8006900. arXiv
  • Rina Okada, Kazuto Fukuchi, and Jun Sakuma. Differentially Private Analysis of Outliers. Machine Learning and Knowledge Discovery in Databases, vol. 9285, 458–473 pages, 2015. doi: 10.1007/978-3-319-23525-7_28. arXiv
  • Kazuto Fukuchi and Jun Sakuma. Neutralized Empirical Risk Minimization with Generalization Neutrality Bound. Machine Learning and Knowledge Discovery in Databases, vol. 8724, 418–433 pages, 2014. doi: 10.1007/978-3-662-44848-9_27.
  • Kazuto Fukuchi, Jun Sakuma, and Toshihiro Kamishima. Prediction with Model-Based Neutrality. Machine Learning and Knowledge Discovery in Databases, vol. 8189, 499–514 pages, 2013. doi: 10.1007/978-3-642-40991-2_32.

Workshop

  • Kazuto Fukuchi, Ryuichiro Hataya, and Kota Matsui. Provable Data Scaling Law for Meta Learning via Complexity Minimization. 4th Workshop on High-dimensional Learning Dynamics (HiLD) (at The Forty-Third International Conference on Machine Learning (ICML 2026)), 2026. arXiv
  • Mitsuhiro Fujikawa, Yohei Akimoto, Jun Sakuma, and Kazuto Fukuchi. Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift. Mathematics of Modern Machine Learning (M3L) (at The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)), 2024. arXiv Poster
  • Kazuto Fukuchi and Jun Sakuma. Minimax Optimal Fair Regression under Linear Model. Algorithmic Fairness through the Lens of Causality and Privacy (at The Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS 2022)), 2022. arXiv Poster

Awards and Honors

  • Kazuto Fukuchi. 2025 Institute of Systems and Information Engineering Best Paper Award. Institute of SystemsInformation Engineering, 2026.
  • Shojiro Yamabe, Kazuto Fukuchi, and Jun Sakuma. JSAI Annual Conference Award 2024. The Japanese Society for Artificial Intelligence (JSAI), 2024.
  • Hideyuki Oiso, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. CSS2023 Student Paper Award. Computer Security Symposium 2023 (CSS2023), 2023.
  • Kazuto Fukuchi and Jun Sakuma. SITA Best Young Researcher Paper Award 2018. The 41th Symposium on Information Theoryits Applications (SITA2019), 2019.
  • Kazuto Fukuchi and Jun Sakuma. Hornable Award of Student Presentation. The 20th Information-Based Induction Sciences Workshop (IBIS), 2017.
  • Kazuya Kakizaki, Kazuto Fukuchi, and Jun Sakuma. CSS2016 Hornable Paper Award. Computer Security Symposium 2016 (CSS2016), 2016.
  • Kazuto Fukuchi. IBM Ph.D. Fellowship Award 2015–2016. IBM, 2016.
  • Rina Okada, Kazuto Fukuchi, and Jun Sakuma. Best Paper Award. The 7th Forum on Data EngineeringInformation Management (DEIM2015), 2015.

Research Funds

  • Kazuto Fukuchi. Clarification of Minimax Optimality of Out-of-Distribution Generalizable Fair Regression Algorithms via Foundation Models. Grant-in-Aid for Scientific Research (B), JSPS KAKENHI Grant Number 26K02874, 2026-2030. Link
  • Kazuto Fukuchi. Clarification of Minimax Optimality in Fair Regression under Demographic Parity. Grant-in-Aid for Early-Career Scientists, JSPS KAKENHI Grant Number 23K13011, 2023-2025. Link
  • Kazuto Fukuchi. Minimax Optimal Functional Estimation on Large-Scale Discrete Distributions. Grant-in-Aid for Early-Career Scientists, JSPS KAKENHI Grant Number 20K19750, 2020-2022. Link
  • Kazuto Fukuchi. Minimax Optimal Estimators for Scalar Values in Discrete Distributions. Grant-in-Aid for JSPS Fellows, JSPS KAKENHI Grant Number 17J01031, 2017-2018. Link

Invited Talks

  • 福地 一斗. 機械学習アルゴリズムに潜む不公平なバイアスとその理論. 2022年電子情報通信学会ソサイエティ大会 AT-1 データサイエンスと情報理論, 2022. Slides
  • Kazuto Fukuchi. Faking Fairness via Stealthily Biased Sampling. ACML 2019 Workshop on Statistics & Machine Learning Researchers in Japan, 2019.
  • 福地 一斗. 公平性を保証したAI/機械学習アルゴリズムの最新理論. 産業技術総合研究所人工知能研究センター 第38回AIセミナー 「機械学習／人工知能の公平性」, 2019. Slides
  • 福地 一斗, 福馬 智生, 永野 雄大. NeurIPS概要・今年の傾向. 第76回人工知能セミナー, 2019.
  • 福地 一斗. 頑健性を持った機械学習. 第76回人工知能セミナー, 2019.
  • 福地 一斗. 公平性に配慮した学習とその理論的課題. 第21回情報論的学習理論ワークショップ (IBIS 2018), 企画セッション：学習理論, 2018. Slides
  • 福地 一斗. 敵対/分配的文脈に対するバンディット学習における結果的公平性. 統計学・機械学習若手シンポジウム「大規模複雑データに対する統計・機械学習のアプローチ」, 2017.
  • Toshihiro Kamishima, Kazuto Fukuchi, Jun Sakuma, Shotaro Akaho, and Hideki Asoh. Future Directions of Fairness-Aware Data Mining: Recommendation, Causality, and Theoretical Aspects. 2nd Workshop on Fairness, Accountability, and Transparency in Machine Learning, 2015.

Preprint (Others)

  • Mitsuhiro Fujikawa, Yohei Akimoto, Jun Sakuma, and Kazuto Fukuchi. Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift. arXiv:2405.16906v2 [stat.ML], 2024. arXiv
  • Yu Zhe, Rei Nagaike, Daiki Nishiyama, Kazuto Fukuchi, and Jun Sakuma. Adversarial Attacks on Hidden Tasks in Multi-Task Learning. arXiv:2405.15244v2 [cs.LG], 2024. arXiv
  • Kazuto Fukuchi and Jun Sakuma. Demographic Parity Constrained Minimax Optimal Regression under Linear Model. arXiv:2206.11546v3 [math.ST], 2023. arXiv
  • Atsuhiro Miyagi, Yoshiki Miyauchi, Atsuo Maki, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Covariance Matrix Adaptation Evolutionary Strategy with Worst-Case Ranking Approximation for Min--Max Optimization and its Application to Berthing Control Tasks. arXiv:2303.16079v1 [cs.NE], 2023. arXiv
  • Takumi Tanabe, Rei Sato, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification. arXiv:2211.03413v2 [cs.LG], 2023. arXiv
  • Atsuhiro Miyagi, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Adaptive Scenario Subset Selection for Worst-Case Optimization and its Application to Well Placement Optimization. arXiv:2211.16574v1 [cs.NE], 2022. arXiv
  • Thien Q. Tran, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation. arXiv:2109.04518v1 [cs.LG], 2021. arXiv
  • Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions. arXiv:2103.01578v2 [cs.NE], 2021. arXiv
  • Thien Q. Tran, Kazuto Fukuchi, Youhei Akimoto, and Jun Sakuma. Statistically Significant Pattern Mining with Ordinal Utility. arXiv:2008.10747v1 [stat.ME], 2020. arXiv
  • Kazuto Fukuchi, Satoshi Hara, and Takanori Maehara. Faking Fairness via Stealthily Biased Sampling. arXiv:1901.08291v2 [stat.ML], 2019. arXiv
  • Kazuto Fukuchi, Chia-Mu Yu, Arashi Haishima, and Jun Sakuma. Locally Differentially Private Minimum Finding. arXiv:1905.11067v1 [math.ST], 2019. arXiv
  • Kazuto Fukuchi and Jun Sakuma. Minimax Optimal Additive Functional Estimation with Discrete Distribution: Slow Divergence Speed Case. arXiv:1801.05362v1 [cs.IT], 2018. arXiv
  • Kazuto Fukuchi and Jun Sakuma. Minimax Optimal Estimators for Additive Scalar Functionals of Discrete Distributions. arXiv:1701.06381v3 [cs.IT], 2017. arXiv
  • Kazuto Fukuchi, Quang Khai Tran, and Jun Sakuma. Differentially Private Empirical Risk Minimization with Input Perturbation. arXiv:1710.07425v1 [stat.ML], 2017. arXiv
  • Kazuto Fukuchi and Jun Sakuma. Neutralized Empirical Risk Minimization with Generalization Neutrality Bound. arXiv:1511.01987v1 [stat.ML], 2015. arXiv
  • Rina Okada, Kazuto Fukuchi, Kazuya Kakizaki, and Jun Sakuma. Differentially Private Analysis of Outliers. arXiv:1507.06763v2 [stat.ML], 2015. arXiv
  • Kazuto Fukuchi and Jun Sakuma. Fairness-Aware Learning with Restriction of Universal Dependency using f-Divergences. arXiv:1506.07721v1 [stat.ML], 2015. arXiv

Conference (in Japanese)

  • 坂田 麻絢, 福地 一斗. 効率的かつ事後的に制御可能な公平性-精度トレードオフを実現する公平な分類手法. 第58回情報論的学習理論と機械学習（IBISML）研究会, vol. 125, 308, pp. 95-102, 2025. Link
  • 坂田 麻絢, 福地 一斗. 分布変換・後処理統合による再学習不要な公平性-精度トレードオフ制御と効率向上. 第28回情報論的学習理論ワークショップ (IBIS2025), 1b-R-44, 2025 (ポスターのみ).
  • 福地 一斗, 幡谷 龍一郎, 松井 孝太. Caulkingによる事前学習モデルの有用性の理論的特徴づけ. 第28回情報論的学習理論ワークショップ (IBIS2025), 1b-R-61, 2025 (ポスターのみ).
  • 下坂 知広, 福地 一斗. 視覚言語モデルを用いたスプリアス相関の低減における欠損グループへの汎化. 第27回情報論的学習理論ワークショップ (IBIS2024), 2-R-018, 2024 (ポスターのみ).
  • 山辺 翔二郎, 福地 一斗, 佐久間 淳. 深層強化学習エージェントの振る舞いの操作を目的とした敵対的攻撃とその防御. コンピュータセキュリティシンポジウム2024（CSS2024）, 3G1-3, pp. 1258-1265, 2024.
  • 吉成 勇人, ユ テツ, 福地 一斗, 佐久間 淳. 自然言語で記述された物体の外見的特徴と画像の類似度に基づく敵対的サンプルの検出. 人工知能学会全国大会(第 38 回)論文集, 2G1-GS-11-05, pp. 1-4, 2024.
  • 山辺 翔二郎, 福地 一斗, 仙田 涼摩, 佐久間 淳. 観測への敵対的摂動を介した模倣学習による深層強化学習エージェントへの標的型操作攻撃. 人工知能学会全国大会(第 38 回)論文集, 2G1-GS-11-03, pp. 1-4, 2024.
  • 戴 晟天, 秋本 洋平, 佐久間 淳, 福地 一斗. Poisoning Attack on Fairness of Fair Classification Algorithm through Threshold Control. 第53回情報論的学習理論と機械学習（IBISML）研究会, vol. 123, 410, pp. 49-56, 2024. Link
  • 藤川 光浩, 秋本 洋平, 佐久間 淳, 福地 一斗. neighbor-transfer-exponentを通した非絶対連続分布間の共変量シフト下での分類誤差解析. 第52回情報論的学習理論と機械学習（IBISML）研究会, vol. 123, 311, pp. 58-65, 2023. Link
  • 大磯 秀幸, 福地 一斗, 秋本 洋平, 佐久間 淳. 物理的に実現可能な特徴をトリガーとしたクリーンラベルバックドア攻撃. コンピュータセキュリティシンポジウム2023（CSS2023）, pp. 1219-1226, 2023.
  • Xu Kaiwen, 福地 一斗, 秋本 洋平, 佐久間 淳. ノックオフによる画像分類器の統計的有意なコンセプトに基づく説明. 人工知能学会全国大会(第 37 回)論文集, 4Q3OS1404, pp. 1-4, 2023.
  • 大磯 秀幸, 福地 一斗, 秋本 洋平, 佐久間 淳. コンセプトをトリガーとしたステルス性の高いバックドア攻撃. 人工知能学会全国大会(第 37 回)論文集, 3L1GS1103, pp. 1-4, 2023.
  • 小路口 望, 福地 一斗, 秋本 洋平, 佐久間 淳. 少数のセンシティブ属性を用いた公平な学習. 人工知能学会全国大会(第 37 回)論文集, 2D4GS205, pp. 1-4, 2023.
  • 西山 大輝, 福地 一斗, 秋本 洋平, 佐久間 淳. 精度劣化を伴わない特定クラスの再現率改善のための分類器学習. 人工知能学会全国大会(第 37 回)論文集, 3D1GS203, pp. 1-4, 2023.
  • 徐 楷文, 福地 一斗, 秋本 洋平, 佐久間 淳. 偽発見率を保証したコンセプトによる説明可能モデルの学習. 人工知能学会全国大会(第 36 回)論文集, 4G1-OS-4a-02, pp. 1-4, 2022.
  • 田邊 拓実, 佐藤 怜, 福地 一斗, 佐久間 淳, 秋本 洋平. モデル化誤差に頑健な Max-Min Off-Policy Actor-Critic. 人工知能学会全国大会(第 36 回)論文集, 2C5-GS-2-03, pp. 1-4, 2022.
  • 森永 大貴, 福地 一斗, 佐久間 淳, 秋本 洋平. (1+1)-Evolution Strategyの凸二次関数における収束速度の導出. 人工知能学会全国大会(第 35 回)論文集, 1H3-GS-1b-03, pp. 1-4, 2021.
  • 江戸 陽向, 濱田 直希, 福地 一斗, 佐久間 淳, 秋本 洋平. 深層生成モデルによる弱パレート解集合の近似. 人工知能学会全国大会(第 35 回)論文集, 1G3-GS-2b-04, pp. 1-4, 2021.
  • 田邊 拓実, 福地 一斗, 佐久間 淳, 秋本 洋平. Sequential Variational Autoencoderを用いたAngry Birdsのステージ生成. 人工知能学会全国大会(第 35 回)論文集, 3G4-GS-2i-04, pp. 1-4, 2021.
  • 阪本 直気, 佐藤 怜, 福地 一斗, 佐久間 淳, 秋本 洋平. 複数の損失関数を用いた深層生成モデルの訓練と制約付きブラックボックス最適化への適用. 人工知能学会全国大会(第 35 回)論文集, 1G3-GS-2b-05, pp. 1-4, 2021.
  • 佐藤 怜, 福地 一斗, 佐久間 淳, 秋本 洋平. 強化学習における遷移確率を用いたドメイン適応による方策の転移. 人工知能学会全国大会(第 34 回) 論文集, 2J5-GS-2-03, pp. 1-4, 2020.
  • 福地 一斗. 分布変動に対する公平な機械学習アルゴリズムの頑健性. 人工知能学会全国大会(第 34 回) 論文集, vol. 3N5-OS-11b-05, 1–4 pages, 2020.
  • 福地 一斗, 佐久間 淳. 離散分布におけるシャノンエントロピー型のAdditive汎関数のミニマックス最適推定. 第41回情報理論とその応用シンポジウム(SITA2018), pp. 1-6, 2018.
  • 小野 元, 福地 一斗, 秋本 洋平, 佐久間 淳. Locally Private Continual Countingにおける1-Shot Reportingメカニズムの有用性解析. コンピュータセキュリティシンポジウム2018論文集, vol. 2018, 2, 801–808 pages, 2018.
  • 小野 元, 福地 一斗, 佐久間 淳. 局所差分プライバシー制約下における逐次heavy hitters検知. 第10回データ工学と情報マネジメントに関するフォーラム （第16回日本データベース学会年次大会）, 1–8 pages, 2018.
  • 中里 佳央, 福地 一斗, 佐久間 淳. 一般化l1正則化問題に対するオンライン最適化手法. 第20回情報論的学習理論ワークショップ(IBIS2017), vol. 117, 293, 93–100 pages, 2017.
  • 福地 一斗, 佐久間 淳. 結果的公平な文脈付きバンディット学習. 第20回情報論的学習理論ワークショップ(IBIS2017), vol. 117, 293, 139–146 pages, 2017.
  • 福地 一斗, 佐久間 淳. 離散分布のエントロピーライクな指標に対するミニマックス最適推定量. 第３９回情報理論とその応用シンポジウム（SITA2016）, 1–6 pages, 2016.
  • 中里 佳央, 福地 一斗, 佐久間 淳. 近接平均を用いた加速近接勾配法の適応的リスタート. 第19回情報論的学習理論ワークショップ(IBISML), vol. 116, 300, 65–71 pages, 2016.
  • 福地 一斗, 佐久間 淳. 離散分布の加法分解可能なスカラー汎関数におけるミニマックス最適推定量. 第19回情報論的学習理論ワークショップ(IBISML), vol. 116, 300, 259–265 pages, 2016.
  • 柿崎 和也, 福地 一斗, 佐久間 淳. カイ二乗検定の幾何的解釈に基づく差分プライバシーの実現. コンピュータセキュリティシンポジウム2016論文集, vol. 2016, 2, 1199–1206 pages, 2016.
  • 岡田 莉奈, 福地 一斗, 佐久間 淳. 差分プライバシを保証した外れ値分析アルゴリズムの高速化. 第18回情報論的学習理論と機械学習ワークショップ (IBIS2015), D-50, 2015 (ポスターのみ).
  • 福地 一斗, 佐久間 淳. 相互情報量の推定におけるMinimax最適推定量. 第18回情報論的学習理論と機械学習ワークショップ (IBIS2015), D-65, 2015 (ポスターのみ).
  • 岡田 莉奈, 福地 一斗, 佐久間 淳. 差分プライバシを保証した外れ値検出. 第7回データ工学と情報マネジメントに関するフォーラム(DEIM2015), vol. G1-3, 1–8 pages, 2015.
  • チャン クワンカイ, 福地 一斗, 佐久間 淳. クラウドセンシングにおける差分プライバシーを保証した線形回帰モデル学習. 情報論的学習理論ワークショップ(IBIS2014), vol. 114, 306, 95–102 pages, 2014.
  • 福地 一斗, 佐久間 淳. 共分散中立性リスクにおける中立経験リスク最小化. 第18回情報論的学習理論と機械学習（IBISML）研究会, vol. 114, 198, pp. 93-100, 2014. Link
  • 福地 一斗, 佐久間 淳. 識別における汎化中立性の保証. 人工知能学会全国大会(第 28 回)論文集, vol. 1g2-4, 1–4 pages, 2014.
  • 川本 淳平, 福地 一斗, 佐久間 淳. マルコフモデルを仮定した位置情報開示のためのアドバーザリアルプライバシ. 人工知能学会全国大会(第 27 回)論文集, vol. 1c4-3, 1–5 pages, 2013.
  • 福地 一斗, 佐久間 淳, 神嶌 敏弘. 分類問題における視点中立化. 人工知能学会全国大会(第 27 回) 論文集, vol. 3L1-OS-06a-2, 1–4 pages, 2013.
  • 川本 淳平, 福地 一斗, 照屋 唯紀, 佐久間 淳. プライバシを考慮した移動系列情報解析のための安全性の提案. 2013年暗号と情報セキュリティシンポジウム (SCIS2013), vol. 2c2-4, 1–8 pages, 2013.