2025/11/19 11:52
[AIP Progress Report Event] AI Security and Privacy Team (Sep. 17, 2025) サムネイル

説明

[AIP Progress Report Event] AI Security and Privacy Team (Sep. 17, 2025)
＊You can start each talk by clicking the time (h:m:s) before the speaker’s name.
00:00:06 Prof. Jun Sakuma (RIKEN AIP / Science Tokyo) “Opening remarks”
00:05:32 Prof. Jun Sakuma (RIKEN AIP / Science Tokyo) “Team Achievements”
00:23:08 Prof. Youhei Akimoto (Tsukuba University) “Stepwise Alignment for Constrained Language Model Policy Optimization”
00:51:56 Prof. Chia-Mu Yu (National Yang Ming Chiao Tung University) “Model Merging Security”
01:32:12 Prof. Qingsong Wei (A*STAR) “Decentralized Trustworthy AI: Federated Learning”
02:04:28 Prof. Jingfeng Zhang (University of Auckland) “Privacy-Preserving Adaptation against Membership Inference Attacks for Latent Diffusion Models”

Event page URL