Toshiya Shimizu

5 papers · 2024–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

AAAI (1) CVPR (1) EACL (1) ECCV (1) WACV (1)

Top co-authors

Omer Hofman (5) Asaf Shabtai (4) Amit Giloni (4) Yuval Elovici (3) Edita Grolman (2) Jonathan Brokman (2) Yarin Yerushalmi Levi (2) Idan Yankelev (2) Roman Vainshtein (2) Oren Rachmil (2)

Research topics

Artificial Intelligence (4) Core AI (4) Computer Vision (3) Machine Learning (3) Analysis (3) Application Areas (3) Learning Types · Machine Learning (2) Deep Learning (1) Learning Types · Deep Learning (1)

Keywords

object detection (3) adversarial robustness (2) anomaly detection (1) uncertainty quantification (1) knowledge distillation (1) explainable ai (1) adversarial training (1) saliency map (1) adversarial attack (1) agent security (1) adversarial patch attack (1) performance degradation (1) adversarial patch (1) large language model (1) zero-shot defense (1) adversarial tuning (1) multilingual agentic system (1) model compression (1) style removal (1) benchmark evaluation (1)

Papers

AntiStyler: Defending Object Detection Models Against Adversarial Patch Attacks Using Style Removal CVPR 2026 MAPS: A Multilingual Benchmark for Agent Performance and Security EACL 2026 DiL: An Explainable and Practical Metric for Abnormal Uncertainty in Object Detection WACV 2025 KDAT: Inherent Adversarial Robustness via Knowledge Distillation with Adversarial Tuning for Object Detection Models AAAI 2025 MONTAGE: Monitoring Training for Attribution of Generative Diffusion Models ECCV 2024