684 citations · 1.2k across the 33 of their papers we have counts for
34 papers
Generalizable Face Forgery Detection via Separable Prompt Learning
Enrui Yang, Baoyuan Wu, Yuezun Li
Detecting face forgeries using CLIP has recently emerged as a promising direction. However, most existing methods focus on adapting its visual encoder, leaving the potential of the…
Detecting Diffusion-generated Images via Dynamic Assembly Forests
Mengxin Fu, Yuezun Li
Diffusion models are known for generating high-quality images, causing serious security concerns. To combat this, most efforts rely on deep neural networks (e.g., CNNs and Transfor…
Off-the-shelf Vision Models Benefit Image Manipulation Localization
Zhengxuan Zhang, Keji Song, Junmin Hu +2
Image manipulation localization (IML) and general vision tasks are typically treated as two separate research directions due to the fundamental differences between manipulation-spe…
Generalizing Video DeepFake Detection by Self-generated Audio-Visual Pseudo-Fakes
Zihe Wei, Yuezun Li
Detecting video deepfakes has become increasingly urgent in recent years. Given the audio-visual information in videos, existing methods typically expose deepfakes by modeling cros…
Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics
Yuezun Li, Delong Zhu, Xinjie Cui +1
The rapid advancement of AI technologies has significantly increased the diversity of DeepFake videos circulating online, posing a pressing challenge for \textit{generalizable fore…
Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection
Delong Zhu, Yuezun Li, Baoyuan Wu +3
Face-swapping DeepFakes have become an escalating societal concern, attracting increasing attention in recent years. To counter this, we investigate a new proactive defense framewo…
Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection
Xinjie Cui, Yuezun Li, Delong Zhu +3
We describe Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLIP is highly versatile, adapting…
Active Fake: DeepFake Camouflage
Pu Sun, Honggang Qi, Yuezun Li
DeepFake technology has gained significant attention due to its ability to manipulate facial attributes with high realism, raising serious societal concerns. Face-Swap DeepFake is…
PhyTracker: An Online Tracker for Phytoplankton
Yang Yu, Qingxuan Lv, Yuezun Li +2
Phytoplankton, a crucial component of aquatic ecosystems, requires efficient monitoring to understand marine ecological processes and environmental conditions. Traditional phytopla…
High-order Neighborhoods Know More: HyperGraph Learning Meets Source-free Unsupervised Domain Adaptation
Jinkun Jiang, Qingxuan Lv, Yuezun Li +4
Source-free Unsupervised Domain Adaptation (SFDA) aims to classify target samples by only accessing a pre-trained source model and unlabelled target samples. Since no source data i…
Texture, Shape, Order, and Relation Matter: A New Transformer Design for Sequential DeepFake Detection
Yunfei Li, Yuezun Li, Baoyuan Wu +3
Sequential DeepFake detection is an emerging task that predicts the manipulation sequence in order. Existing methods typically formulate it as an image-to-sequence problem, employi…
FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
Hanzhe Li, Jiaran Zhou, Yuezun Li +3
Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these face…
Mumpy: Multilateral Temporal-view Pyramid Transformer for Video Inpainting Detection
Ying Zhang, Yuezun Li, Bo Peng +3
The task of video inpainting detection is to expose the pixel-level inpainted regions within a video sequence. Existing methods usually focus on leveraging spatial and temporal inc…
DomainForensics: Exposing Face Forgery across Domains via Bi-directional Adaptation
Qingxuan Lv, Yuezun Li, Junyu Dong +4
Recent DeepFake detection methods have shown excellent performance on public datasets but are significantly degraded on new forgeries. Solving this problem is important, as new for…
COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection
Cong Zhang, Honggang Qi, Shuhui Wang +2
DeepFakes have raised serious societal concerns, leading to a great surge in detection-based forensics methods in recent years. Face forgery recognition is a standard detection met…
ForensicsForest Family: A Series of Multi-scale Hierarchical Cascade Forests for Detecting GAN-generated Faces
Jiucui Lu, Jiaran Zhou, Junyu Dong +3
The prominent progress in generative models has significantly improved the reality of generated faces, bringing serious concerns to society. Since recent GAN-generated faces are in…
FakeTracer: Catching Face-swap DeepFakes via Implanting Traces in Training
Pu Sun, Honggang Qi, Yuezun Li +1
Face-swap DeepFake is an emerging AI-based face forgery technique that can replace the original face in a video with a generated face of the target identity while retaining consist…
Enhancing the Transferability via Feature-Momentum Adversarial Attack
Xianglong, Yuezun Li, Haipeng Qu +1
Transferable adversarial attack has drawn increasing attention due to their practical threaten to real-world applications. In particular, the feature-level adversarial attack is on…
DFGC 2021: A DeepFake Game Competition
Bo Peng, Hongxing Fan, Wei Wang +20
This paper presents a summary of the DFGC 2021 competition. DeepFake technology is developing fast, and realistic face-swaps are increasingly deceiving and hard to detect. At the s…
DeepFake-o-meter: An Open Platform for DeepFake Detection
Yuezun Li, Cong Zhang, Pu Sun +2
In recent years, the advent of deep learning-based techniques and the significant reduction in the cost of computation resulted in the feasibility of creating realistic videos of h…
Landmark Breaker: Obstructing DeepFake By Disturbing Landmark Extraction
Pu Sun, Yuezun Li, Honggang Qi +1
The recent development of Deep Neural Networks (DNN) has significantly increased the realism of AI-synthesized faces, with the most notable examples being the DeepFakes. The DeepFa…
Invisible Backdoor Attack with Sample-Specific Triggers
Yuezun Li, Yiming Li, Baoyuan Wu +3
Recently, backdoor attacks pose a new security threat to the training process of deep neural networks (DNNs). Attackers intend to inject hidden backdoors into DNNs, such that the a…
LandmarkGAN: Synthesizing Faces from Landmarks
Pu Sun, Yuezun Li, Honggang Qi +1
Face synthesis is an important problem in computer vision with many applications. In this work, we describe a new method, namely LandmarkGAN, to synthesize faces based on facial la…
Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights
Shu Hu, Yuezun Li, Siwei Lyu
Sophisticated generative adversary network (GAN) models are now able to synthesize highly realistic human faces that are difficult to discern from real ones visually. In this work,…