Recent | Futa Waseda

Semantic Color Naturalness Breaker: Preventing Illegitimate Colorization via Content-Aware Color Priors

Mon, 05 Oct 2026 00:00:00 +0000

Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models

Tue, 01 Sep 2026 00:00:00 +0000

TL;DR: VLMs must sometimes read text in images and sometimes ignore it — but no model does both well. We propose RIO-Bench, the first benchmark unifying typographic-attack robustness and text recognition evaluation. We further introduce a data-driven defense that adaptively selects when to use in-image text, outperforming prior non-adaptive approaches.

Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models

Mon, 01 Jun 2026 00:00:00 +0000

Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness

Fri, 01 May 2026 00:00:00 +0000

Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships

Fri, 06 Mar 2026 00:00:00 +0000

Quality Text, Robust Vision: The Role of Language in Enhancing Visual Robustness of Vision-Language Models

Mon, 27 Oct 2025 00:00:00 +0000

Uncolorable Examples: Preventing Unauthorized AI Colorization via Perception-Aware Chroma-Restrictive Perturbation

Wed, 22 Oct 2025 00:00:00 +0000

MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models

Sun, 27 Jul 2025 00:00:00 +0000

Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off

Thu, 24 Apr 2025 00:00:00 +0000

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection

Sun, 27 Oct 2024 00:00:00 +0000

Beyond In-Domain Scenarios: Robust Density-Aware Calibration

Sun, 23 Jul 2023 00:00:00 +0000

Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differently

Tue, 03 Jan 2023 00:00:00 +0000