10 papers
Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse
Futa Waseda, Shuhei Kurita, Isao Echizen
Vision-language-action (VLA) models adapt pretrained vision-language models (VLMs) for closed-loop robot control, transferring their perceptual and semantic capabilities to action…
Rethinking Brain Decoding with CLIP: The Role of Adversarial Robustness
Byeongseo Bok, Futa Waseda, Jun Liu +1
Brain decoding aims to uncover neural mechanisms by inferring stimulus-related representations from brain signals. In fMRI studies, this is typically achieved by mapping fMRI respo…
When LLM Rationales Become User-Facing: Effects on Trust Perception, Decision-Making, and Gaze Behaviors
Xin Sun, Ting Pan, Yajing Wang +5
Large language models (LLMs) increasingly show step-by-step reasoning rationales alongside their answers, turning reasoning from an internal model capability into a user-facing int…
Forged Calamity: Benchmark for Cross-Domain Synthetic Disaster Detection in the Age of Diffusion
Duc-Manh Phan, Quoc-Duy Tran, Duy-Khang Do +9
The rapid advancement of text-to-image diffusion models has enabled the creation of highly photorealistic synthetic images that closely resemble real photographs, making it increas…
EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection
Chenyang Zhu, Maorong Wang, Jun Liu +2
The rapid proliferation of AI-Generated Images (AIGIs) poses severe misinformation risks, making AIGI detection critical yet challenging. Traditional detection paradigms mainly rel…
Seeing the Reasoning: How LLM Rationales Influence User Trust and Decision-Making in Factual Verification Tasks
Xin Sun, Shu Wei, Jos A Bosch +3
Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are ty…
Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
Jun Liu, Leo Yu Zhang, Fengpeng Li +2
Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models. Despite recent progress, existing approaches…
SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
Hongbo Wang, AprilPyone MaungMaung, Isao Echizen
Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal understanding but inherit toxic signals from weakl…
Quality Text, Robust Vision: The Role of Language in Enhancing Visual Robustness of Vision-Language Models
Futa Waseda, Saku Sugawara, Isao Echizen
Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including ima…
DRAGON: A Large-Scale Dataset of Realistic Images Generated by Diffusion Models
Giulia Bertazzini, Daniele Baracchi, Dasara Shullani +2
The remarkable ease of use of diffusion models for image generation has led to a proliferation of synthetic content online. While these models are often employed for legitimate pur…