Area of research
Computer Vision and Pattern Recognition
Research interest
Research interests include Advanced Steganography and Watermarking Techniques, Digital Media Forensic Detection, Chaos-based Image/Signal Encryption, and Generative Adversarial Networks and Image Synthesis.
Generalized Document Tampering Localization via Color and Semantic Disentanglement
Active Adversarial Noise Suppression for Image Forgery Localization
DiffEraser: Generalized Text Erasure Based on Latent Diffusion Prior
VoIP Call Identification via a Dual-Level 1D-CNN With Frame and Utterance Features
Query-Efficient Hard-Label Attacks Against Black-Box Image Forgery Localization Model via Reinforcement Learning
Secure Moving Object Detection in Compressed Video Using Attentions
Enhancing JPEG Steganography with GANs via Adaptive Modification Loss and Random Masking
Forgery-Aware Adaptive Learning With Vision Transformer for Generalized Face Forgery Detection
Towards JPEG-Resistant Image Forgery Detection and Localization Via Self-Supervised Domain Adaptation
Generating Higher-Quality Anti-Forensics DeepFakes with Adversarial Sharpening Mask
Generating Higher-Quality Anti-Forensics DeepFakes with Adversarial Sharpening Mask
Inter-frame residual frequency-based reconstruction learning for deep video frame interpolation detection
DiRLoc: Disentanglement Representation Learning for Robust Image Forgery Localization
Prompt Engineering-Assisted Malware Dynamic Analysis Using GPT-4
Elastic Supernet with Dynamic Training for JPEG steganalysis
Towards generalizable and robust image tampering localization with multi-task learning and contrastive learning
Adv-Inversion: Stealthy Adversarial Attacks via GAN-Inversion for Facial Privacy Protection
Evading Detection Actively: Toward Anti-Forensics Against Forgery Localization
Moiré Spectral Augmentation and Masked Frequency Modeling for Document Presentation Attack Detection
Unmask Tampering: Efficient Document Tampering Localization under Recapturing Attacks with Real Distortion Knowledge
Accurate and Efficient Privacy-Preserving Feature Extraction on Encrypted Images
A Forensic Framework With Diverse Data Generation for Generalizable Forgery Localization
Privacy-Preserving CNN Inference for Image Super-Resolution Cross Multiple Ciphertexts
StealthPhase: Toward a Stealthy Backdoor Attack Against Speaker Recognition
Universal forged image detection and localization via self-supervised data generation and large-scale model adaptation
FGMIA: Feature-Guided Model Inversion Attacks Against Face Recognition Models
Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection
Steganography Embedding Cost Learning With Generative Multi-Adversarial Network
One-Class Neural Network With Directed Statistics Pooling for Spoofing Speech Detection
One-Class Neural Network With Directed Statistics Pooling for Spoofing Speech Detection