77 citations · 79 across the 9 of their papers we have counts for
9 papers
Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria
Nuoyan Zhou, Nannan Wang, Decheng Liu +2
Deep neural networks are vulnerable to adversarial noise. Adversarial Training (AT) has been demonstrated to be the most effective defense strategy to protect neural networks from…
Gradient constrained sharpness-aware prompt learning for vision-language models
Liangchen Liu, Nannan Wang, Dawei Zhou +4
This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i.e., improving the performance on unseen classes while maintaining…
Attention Consistency Refined Masked Frequency Forgery Representation for Generalizing Face Forgery Detection
Decheng Liu, Tao Chen, Chunlei Peng +3
Due to the successful development of deep image generation technology, visual data forgery detection would play a more important role in social and economic security. Existing forg…
MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection
Ruiyang Xia, Decheng Liu, Jie Li +3
Advanced manipulation techniques have provided criminals with opportunities to make social panic or gain illicit profits through the generation of deceptive media, such as forged f…
Hierarchical Forgery Classifier On Multi-modality Face Forgery Clues
Decheng Liu, Zeyang Zheng, Chunlei Peng +3
Face forgery detection plays an important role in personal privacy and social security. With the development of adversarial generative models, high-quality forgery images become mo…
FedForgery: Generalized Face Forgery Detection with Residual Federated Learning
Decheng Liu, Zhan Dang, Chunlei Peng +4
With the continuous development of deep learning in the field of image generation models, a large number of vivid forged faces have been generated and spread on the Internet. These…
Hiding Visual Information via Obfuscating Adversarial Perturbations
Zhigang Su, Dawei Zhou, Nannan Wangu +3
Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection. Existing adversarial perturbations-b…
TransFA: Transformer-based Representation for Face Attribute Evaluation
Decheng Liu, Weijie He, Chunlei Peng +3
Face attribute evaluation plays an important role in video surveillance and face analysis. Although methods based on convolution neural networks have made great progress, they inev…
Spatial-Temporal Frequency Forgery Clue for Video Forgery Detection in VIS and NIR Scenario
Yukai Wang, Chunlei Peng, Decheng Liu +2
In recent years, with the rapid development of face editing and generation, more and more fake videos are circulating on social media, which has caused extreme public concerns. Exi…