3 papers
cs.CR2025
AI Security Map: Holistic Organization of AI Security Technologies and Impacts on Stakeholders
Hiroya Kato, Kentaro Kita, Kento Hasegawa +1
As the social implementation of AI has been steadily progressing, research and development related to AI security has also been increasing. However, existing studies have been limi…
cs.AI2025
Annealing Machine-assisted Learning of Graph Neural Network for Combinatorial Optimization
Pablo Loyola, Kento Hasegawa, Andres Hoyos-Idobro +4
While Annealing Machines (AM) have shown increasing capabilities in solving complex combinatorial problems, positioning themselves as a more immediate alternative to the expected a…
cs.CR2023
EdgePruner: Poisoned Edge Pruning in Graph Contrastive Learning
Hiroya Kato, Kento Hasegawa, Seira Hidano +1
Graph Contrastive Learning (GCL) is unsupervised graph representation learning that can obtain useful representation of unknown nodes. The node representation can be utilized as fe…