ジャーナル論文 / Journal
  1. Sun, Y., Ochiai, H., and Sakuma, J., "Attacking Distance-aware Attack: Semi-targeted Model Poisoning on Federated Learning", IEEE Trans. Artif. Intell. 5(2), 925–939, (2024).
  2. NISHIYAMA, D., FUKUCHI, K., AKIMOTO, Y., and SAKUMA, J., "CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy", IEICE Trans. Inf. Syst. E106.D(4), 523–537, (2023).
  3. Miyagi, A., Miyauchi, Y., Maki, A., Fukuchi, K., Sakuma, J., and Akimoto, Y., "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 3(2), 1–32, (2023).
  4. Tsukada, T., and Unno, H., "Software model-checking as cyclic-proof search.", Proc. ACM Program. Lang. 6(POPL), 1–29, (2022).
  5. Sun, Y., and Ochiai, H., "Homogeneous Learning: Self-Attention Decentralized Deep Learning", IEEE Access 10, 7695–7703, (2022).
  6. Andrew, T. W., Koepke, L. S., Wang, Y., Lopez, M., Steininger, H., Struck, D., Boyko, T., Ambrosi, T. H., Tong, X., Sun, Y., Gulati, G. S., Murphy, M. P., Marecic, O., Telvin, R., Schallmoser, K., Strunk, D., Seita, J., Goodman, S. B., Yang, F., Longaker, M. T., Yang, G. P., and Chan, C. K., "Sexually dimorphic estrogen sensing in skeletal stem cells controls skeletal regeneration", Nat. Commun. 13(1), 6491, (2022).
  7. Sun, Y., Ochiai, H., and Esaki, H., "Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness", IEEE Transactions on Artificial Intelligence 3(6), 963–972, (2021).
国際会議 / Proceedings
  1. Sun, Y., Ochiai, H., and Sakuma, J., "Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation Space", 2024 International Joint Conference on Neural Networks, (2024).
  2. Pham, T., Shimizu, S., Hino, H., and Le, T., "Scalable counterfactual distribution estimation in multivariate causal models", Proceedings of the Third Conference on Causal Learning and Reasoning, PMLR 236, 1118–1140, (2024).
  3. Xu, K., Fukuchi, K., Akimoto, Y., and Sakuma, J., "Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs", Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 519–526, (2023).
  4. Sun, Y., Ochiai, H., Wu, Z., Lin, S., and Kanai, R., "Associative Transformer is a Sparse Representation Learner", NeurIPS 2023 Associative Memory & Hopfield Networks workshop, (2023).
  5. Mori, J., Furukawa, R., Teranishi, I., and Sakuma, J., "Heterogeneous Domain Adaptation with Positive and Unlabeled Data", 2023 IEEE International Conference on Big Data (BigData) 00, 778–787, (2023).
  6. Sun, Y., Ochiai, H., and Sakuma, J., "Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis", 2022 International Joint Conference on Neural Networks (IJCNN) 00, 1–8, (2022).
  7. Sun, Y., Chong, N., and Ochiai, H., "Feature Distribution Matching for Federated Domain Generalization", Asian Conference on Machine Learning, (2022).
  8. Sato, R., Sakuma, J., and Akimoto, Y., "AdvantageNAS - Efficient Neural Architecture Search with Credit Assignment.", Aaai, 9489–9496, (2022).
  9. Unno, H., Terauchi, T., and Koskinen, E., "Constraint-Based Relational Verification.", Cav, 742–766, (2021).
  10. Tanabe, T., Fukuchi, K., Sakuma, J., and Akimoto, Y., "Level generation for angry birds with sequential VAE and latent variable evolution.", Gecco, 1052–1060, (2021).
  11. Morinaga, D., Fukuchi, K., Sakuma, J., and Akimoto, Y., "Convergence rate of the (1+1)-evolution strategy with success-based step-size adaptation on convex quadratic functions.", Gecco, 1169–1177, (2021).
  12. Miyagi, A., Fukuchi, K., Sakuma, J., and Akimoto, Y., "Adaptive scenario subset selection for min-max black-box continuous optimization.", Gecco, 697–705, (2021).
  13. Matsuura, T., Hasegawa, A. A., Akiyama, M., and Mori, T., "Careless Participants Are Essential for Our Phishing Study: Understanding the Impact of Screening Methods.", EuroUSEC, 36–47, (2021).
  14. Matsuura, T., Hasegawa, A. A., Akiyama, M., and Mori, T., "Careless Participants Are Essential for Our Phishing Study - Understanding the Impact of Screening Methods.", EuroUSEC, 36–47, (2021).
  15. Kura, S., Unno, H., and Hasuo, I., "Decision Tree Learning in CEGIS-Based Termination Analysis.", Cav, 75–98, (2021).
  16. Kobayashi, N., Sekiyama, T., Sato, I., and Unno, H., "Toward Neural-Network-Guided Program Synthesis and Verification.", Sas, 236–260, (2021).
  17. Kawaoka, R., Chiba, D., Watanabe, T., Akiyama, M., and Mori, T., "A First Look at COVID-19 Domain Names: Origin and Implications.", Pam, 39–53, (2021).
  18. Kakizaki, K., Miyagawa, T., Singh, I., and Sakuma, J., "Toward Practical Adversarial Attacks on Face Verification Systems.", Biosig, 113–124, (2021).
  19. Hasegawa, A. A., Yamashita, N., Akiyama, M., and Mori, T., "Why They Ignore English Emails: The Challenges of Non-Native Speakers in Identifying Phishing Emails.", SOUPS @ USENIX Security Symposium, 319–338, (2021).
  20. Akimoto, Y., "Saddle point optimization with approximate minimization oracle.", Gecco, 493–501, (2021).