4 papers
Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition Models
Songyan Xie, Jinghang Wen, Encheng Su +1
Near-infrared (NIR) face recognition systems, which can operate effectively in low-light conditions or in the presence of makeup, exhibit vulnerabilities when subjected to physical…
Diffusion-based Virtual Staining from Polarimetric Mueller Matrix Imaging
Xiaoyu Zheng, Jing Wen, Jiaxin Zhuang +6
Polarization, as a new optical imaging tool, has been explored to assist in the diagnosis of pathology. Moreover, converting the polarimetric Mueller Matrix (MM) to standardized st…
PuFace: Defending against Facial Cloaking Attacks for Facial Recognition Models
Jing Wen
The recently proposed facial cloaking attacks add invisible perturbation (cloaks) to facial images to protect users from being recognized by unauthorized facial recognition models.…
HOLMES: to Detect Adversarial Examples with Multiple Detectors
Jing Wen
Deep neural networks (DNNs) can easily be cheated by some imperceptible but purposeful noise added to images, and erroneously classify them. Previous defensive work mostly focused…