SSDL 2021
Safety & Security of Deep Learning 2021

Table of Contents

• Preface
  Summary: There were 12 papers submitted for peer-review to this workshop. Out of these, 9 regular papers were accepted for this volume.

Session 1:

• Lip Forgery Video Detection via Multi-Phoneme Selection
  Jiaying Lin, Wenbo Zhou, Honggu Liu, Hang Zhou, Weiming Zhang, Nenghai Yu
• Self-Supervised Deepfake Detection by Discovering Artifact Discrepancies
  Kai Hong, Xiaoyu Du
• HCF-Net: Hybrid Coarse-to-Fine Network for Forgery Reconstruction
  Long Zhuo, Shunquan Tan
• Exploring the Asynchronous of the Frequency Spectra of GAN-Generated Facial Images
  Le Minh Binh, Simon S. Woo
• Detecting Deepfakes with Multi-Metric Loss
  Ziwei Zhang, Xin Li, Rongrong Ni, Yao Zhao

Session 2:

• Fingerprint Liveness Detection via Learning Multi-Modal Deep Features
  Chengsheng Yuan, Mingyu Chen
• Reversible Adversarial Attack Based on Reversible Image Transformation
  Zhaoxia Yin, Hua Wang, Li Chen, Jie Wang, Weiming Zhang
• Towards Image Data Hiding via Facial Stego Synthesis With Generative Model
  Li Dong, Jie Wang, Rangding Wang, Yuanman Li, Weiwei Sun
• Detection of Adversarial Supports in Few-Shot Classifiers Using Self-Similarity and Filtering
  Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun, Ngai-Man Cheung, Yuval Elovici, Alexander Binder