4 members from our laboratory presented their research at The 37th Annual Conference of the Japanese Society for Artificial Intelligence, 2023 (JSAI2023). The presentations included
- CAMRI Loss: Improving the Recall of Prescribed Classes without Sacrificing Accuracy [西山 大輝, 福地 一斗, 秋本 洋平, and 佐久間 淳(2023)]
- Fair Learning with a Small Number of Sensitive Attributes [小路口 望, 福地 一斗, 秋本 洋平, and 佐久間 淳(2023)]
- Backdoor Attacks using the Concepts as a Trigger [大磯 秀幸, 福地 一斗, 秋本 洋平, and 佐久間 淳(2023)]
- Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs (missing reference)
Related publications
- 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. 電子情報通信学会技術研究報告 , Vol.123 , No.311 , pp.58-65 , 2023 .
- Demographic Parity Constrained Minimax Optimal Regression under Linear Model. In Advances in Neural Information Processing Systems , Vol.36 , pp.8653--8689 , 2023 .
- neighbor-transfer-exponentを用いた非絶対連続分布間の転移学習の誤差解析. 情報論的学習理論ワークショップ , Vol.IBIS2023 , pp.- , 2023 .
- Statistically Significant Pattern Mining with Ordinal Utility. IEEE Transactions on Knowledge and Data Engineering , Vol.35 , No.9 , pp.8770-8783 , 2023 . doi: 10.1109/TKDE.2022.3208626.
- Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, (IJCAI-23) , Vol. , No.8 , pp.519-526 , 2023 . doi: 10.24963/IJCAI.2023/58. arXiv
- 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論文集 , Vol.JSAI2023 , pp.3D1GS203-3D1GS203 , 2023 . doi: 10.11517/pjsai.JSAI2023.0_3D1GS203.
- 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論文集 , Vol.JSAI2023 , pp.4Q3OS1404-4Q3OS1404 , 2023 . doi: 10.11517/pjsai.JSAI2023.0_4Q3OS1404.
- 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論文集 , Vol.JSAI2023 , pp.3L1GS1103-3L1GS1103 , 2023 . doi: 10.11517/pjsai.JSAI2023.0_3L1GS1103.
- 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論文集 , Vol.JSAI2023 , pp.2D4GS205-2D4GS205 , 2023 . doi: 10.11517/pjsai.JSAI2023.0_2D4GS205.
- Unauthorized AI cannot recognize me: Reversible adversarial example. Pattern Recognition , Vol.134 , pp.109048 , 2023 . doi: 10.1016/j.patcog.2022.109048.
- Certified Defense for Content Based Image Retrieval. In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) , pp.4561-4570 , 2023 .
- Minimax Optimal Fair Regression under Linear Model. In NeurIPS 2022 Workshop: Algorithmic Fairness through the Lens of Causality and Privacy . arXiv
- Domain Generalization via Adversarial Learned Novel Domains. In 2022 IEEE International Conference on Multimedia and Expo (ICME) , pp.1–6 , 2022 . doi: 10.1109/ICME52920.2022.9860025.
- CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy. In 2022 International Joint Conference on Neural Networks (IJCNN) , pp.1–8 , 2022 . doi: 10.1109/IJCNN55064.2022.9892108.
- Did You Use My GAN to Generate Fake? Post-hoc Attribution of GAN Generated Images via Latent Recovery. In 2022 International Joint Conference on Neural Networks (IJCNN) , pp.1–8 , 2022 . doi: 10.1109/IJCNN55064.2022.9892704.
- Locally Differentially Private Minimum Finding. IEICE Transactions on Information and Systems , Vol.E105-D , No.8 , pp.1418-1430 , 2022 . doi: 10.1587/transinf.2021EDP7187. arXiv
- Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation. In The Thirty-Sixth AAAI Conference on Artificial Intelligence , Vol.36 , No.9 , pp.9614-9622 , 2022 . doi: 10.1609/aaai.v36i9.21195. arXiv
- Domain Generalization via Adversarially Learned Novel Domains. IEEE Access , Vol.10 , No. , pp.101855-101868 , 2022 . doi: 10.1109/ACCESS.2022.3209815.
- Statistically Significant Pattern Mining with Ordinal Utility. In KDD ’20: The 26th ACM SIGKDD Conference on Knowledge Discoveryand Data Mining , pp.1645–1655 , 2020 . doi: 10.1145/3394486.3403215. arXiv
- Faking Fairness via Stealthily Biased Sampling. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, Special Track on AI for Social Impact , Vol.34 , No.01 , pp.412-419 , 2020 . doi: 10.1609/aaai.v34i01.5377. arXiv
- Minimax Optimal Additive Functional Estimation with Discrete Distribution: Slow Divergence Speed Case. In 2018 IEEE International Symposium on Information Theory (ISIT) , pp.1041-1045 , 2018 . doi: 10.1109/ISIT.2018.8437725. arXiv
- Differentially Private Empirical Risk Minimization with Input Perturbation. In Discovery Science , Vol.10558 , pp.82–90 , 2017 . doi: 10.1007/978-3-319-67786-6_6. arXiv
- Differentially Private Chi-squared Test by Unit Circle Mechanism. In Proceedings of the 34th International Conference on Machine Learning , Vol.70 , pp.1761–1770 , 2017 .
- Minimax optimal estimators for additive scalar functionals of discrete distributions. In 2017 IEEE International Symposium on Information Theory (ISIT) , Vol. , No. , pp.2103-2107 , 2017 . doi: 10.1109/ISIT.2017.8006900. arXiv
- Prediction with Model-Based Neutrality. IEICE Transactions on Information and Systems , Vol.E98.D , No.8 , pp.1503-1516 , 2015 . doi: 10.1587/transinf.2014EDP7367.
- Differentially Private Analysis of Outliers. In Machine Learning and Knowledge Discovery in Databases , Vol.9285 , pp.458–473 , 2015 . doi: 10.1007/978-3-319-23525-7_28. arXiv
- Neutralized Empirical Risk Minimization with Generalization Neutrality Bound. In Machine Learning and Knowledge Discovery in Databases , Vol.8724 , pp.418–433 , 2014 . doi: 10.1007/978-3-662-44848-9_27. arXiv
- Prediction with Model-Based Neutrality. In Machine Learning and Knowledge Discovery in Databases , Vol.8189 , pp.499–514 , 2013 . doi: 10.1007/978-3-642-40991-2_32.