6 papers
Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
Tsubasa Takahashi, Shojiro Yamabe, Futa Waseda +1
Differential Attention (DA) has been proposed as a refinement to standard attention, suppressing redundant or noisy context through a subtractive structure and thereby reducing con…
Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
Shojiro Yamabe, Jun Sakuma
Diffusion language models (DLMs) generate tokens in parallel through iterative denoising, which can reduce latency and enable bidirectional conditioning. However, the safety risks…
Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
Shojiro Yamabe, Kazuto Fukuchi, Jun Sakuma
This study investigates behavior-targeted attacks on reinforcement learning and their countermeasures. Behavior-targeted attacks aim to manipulate the victim's behavior as desired…
Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
Futa Waseda, Shojiro Yamabe, Daiki Shiono +2
Large vision-language models (LVLMs) are vulnerable to typographic attacks, where misleading text inserted into an image can override visual understanding. However, existing evalua…
Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
Shojiro Yamabe, Futa Waseda, Daiki Shiono +1
Recent large vision-language models (LVLMs) have been applied to diverse VQA tasks. However, achieving practical performance typically requires task-specific fine-tuning with large…
MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models
Shojiro Yamabe, Futa Waseda, Tsubasa Takahashi +1
Protecting the intellectual property of Large Language Models (LLMs) has become increasingly critical due to the high cost of training. Model merging, which integrates multiple exp…