Scholar
Toshiki Shibahara
Google Scholar ID: udRFUnoAAAAJ
NTT Social Informatics Laboratories
Cyber Security
Machine Learning
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
516
H-index
10
i10-index
11
Publications
20
Co-authors
0
Publications
6 items
Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs
2026
Cited
0
The Impact of Micro-level User Interventions on Macro-level Misinformation Spread
2026
Cited
0
Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation
2025
Cited
0
Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets
2025
Cited
0
Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
2025
Cited
0
Network Prebunking Problem: Optimizing Prebunking Targets to Suppress the Spread of Misinformation in Social Networks
2025
Cited
0
