Publications

(2026). Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models. ECCV 2026.

PDF

(2026). Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models. CVPR 2026.

PDF

(2026). Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness. ICLR 2026.

PDF

(2026). Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships. WACV 2026.

PDF

(2025). Uncolorable Examples: Preventing Unauthorized AI Colorization via Perception-Aware Chroma-Restrictive Perturbation. APSIPA ASC 2025.

PDF

(2025). MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models. ACL 2025 Main.

PDF

(2024). Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection. ICIP 2024.

PDF

(2023). Beyond In-Domain Scenarios: Robust Density-Aware Calibration. ICML 2023.

PDF

(2023). Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differently. WACV 2023.

PDF Poster

(2019). 消費者アンケートを活用した飲食店顧客の多面的理解. DEIM 2019.

Conference Link PDF