5 papers
Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM
Peiyang Xu, Xiaopei Zhu, Jun Zhu +1
Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as over-reliance on textual co-oc…
Mirror Illusion Art
Xiaopei Zhu, Zeyuan Li, Jun Zhu +1
Mirror Illusion Art is a novel reflection-conditioned 3D illusion where one object yields two target appearances (front and mirror). The task is formulated as inverse design from t…
Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern
Xiaopei Zhu, Guanning Zeng, Zhanhao Hu +2
Visible-thermal (RGB-T) object detection is a crucial technology for applications such as autonomous driving, where multimodal fusion enhances performance in challenging conditions…
Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition
Wei Zhang, Xinyu Chang, Xiao Li +2
Adversarial examples present significant challenges to the security of Deep Neural Network (DNN) applications. Specifically, there are patch-based and texture-based attacks that ar…
Natural Language Induced Adversarial Images
Xiaopei Zhu, Peiyang Xu, Guanning Zeng +2
Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks o…