6 papers
SF-RAG: Structure-Fidelity Retrieval-Augmented Generation for Academic Question Answering
Rui Yu, Tianyi Wang, Ruixia Liu +1
Efficient question-answering (QA) over extensive scientific literature is essential for evidence-based engineering decision-making. Retrieval-augmented generation (RAG) is increasi…
Word-Anchored Temporal Forgery Localization
Tianyi Wang, Xi Shao, Harry Cheng +2
Current temporal forgery localization (TFL) approaches typically rely on temporal boundary regression or continuous frame-level anomaly detection paradigms to derive candidate forg…
Robust Identity Perceptual Watermark Against Deepfake Face Swapping
Tianyi Wang, Mengxiao Huang, Harry Cheng +2
Notwithstanding offering convenience and entertainment to society, Deepfake face swapping has caused critical privacy issues with the rapid development of deep generative models. D…
A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection
Libo Lv, Tianyi Wang, Mengxiao Huang +2
With the rapid advancement of real-time deepfake generation techniques, forged content is becoming increasingly realistic and widespread across applications like video conferencing…
NullSwap: Proactive Identity Cloaking Against Deepfake Face Swapping
Tianyi Wang, Harry Cheng, Xiao Zhang +1
Suffering from performance bottlenecks in passively detecting high-quality Deepfake images due to the advancement of generative models, proactive perturbations offer a promising ap…
Deepfake Detection: A Comprehensive Survey from the Reliability Perspective
Tianyi Wang, Xin Liao, Kam Pui Chow +2
The mushroomed Deepfake synthetic materials circulated on the internet have raised a profound social impact on politicians, celebrities, and individuals worldwide. In this survey,…