Huan Liu

Huan Liu

Auto-generated profile, based on publicly available information

Huan Liu

Institute of Information Science, Beijing Jiaotong University, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 January 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
CMChangtao Miao
Changtao Miao
ZTZichang Tan
Zichang Tan
QCQi Chu
Qi Chu
HLHuan Liu
Huan Liu
HHHonggang Hu
Honggang Hu
NYNenghai Yu
Nenghai Yu
In recent years, face forgery detectors have aroused great interest and achieved impressive performance, but they are still struggling with generalization and robustness. In this work, we explore taking full advantage of the fine-grained forgery traces in both spatial and frequency domains to alleviate this issue. Specifically, we propose a novel High-Frequency Fine-Grained Transformer (F 2 Trans) network which contains two important components, namely Central Difference Attention (CDA) and High-frequency Wavelet Sampler (HWS). The premier CDA module is capable of capturing invariant fine-grained manipulation patterns by aggregating both pixel-level intensity and gradient information of the query to generate key and value pairs. Subsequently, the proposed HWS discards the low-frequency components of wavelet transformation and hierarchically explores high-frequency forgery cues of feature maps, which prevents model confusion caused by low-frequency components and pays attention to local frequency information. In addition, HWS can be employed as a special pooling layer for the F 2 Trans architecture to produce hierarchical feature representations in the spatial-frequency domain. Extensive experiments on multiple popular benchmarks demonstrate the generalization and robustness of the specially designed F 2 Trans framework is well-tailored for face forgery detection when confronting the cross-dataset, cross-manipulation, and unseen perturbations.

20 June 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
RTRenshuai Tao
Renshuai Tao
CTChuangchuang Tan
Chuangchuang Tan
HLHuan Liu
Huan Liu
JWJiakai Wang
Jiakai Wang
Haotong QinHaotong Qin
Haotong Qin
YZYao Zhao
Yao Zhao
Deepfake detection presents a significant challenge, particularly when the available training data is constrained to a limited set of semantic categories—a common and realistic scenario. In deepfake detection, the training labels typically indicate whether an image is real or fake, without specifying the semantic content, such as object classes. Moreover, we cannot know in advance the object categories present in an image to be detected. Ideally, a deepfake detection model should perform consistently across different semantic categories during inference, irrespective of the content. However, existing methods often exhibit significant performance bias between seen and unseen classes, struggling to generalize effectively. To address this issue, we propose Semantic-AGnostic artifact Network (SAGNet), an innovative and efficient approach designed to decouple semantic-agnostic artifacts from content-specific distributions in the training data. Our method eliminates semantic-specific biases, ensuring that the model focuses on universal artifacts related to image authenticity rather than content-dependent features. By employing this decoupling strategy, SAGNet greatly enhances the model’s generalization capacity, even when trained on limited data. Remarkably, through experiments, we demonstrate that SAGNet achieves performance comparable to models trained with 10 times more data, despite being trained on only 2 classes (comparing SAGNet trained on 2 classes in Table I with Ojha [1] trained on 20 categories in Table IV). Furthermore, through extensive experiments, we show that SAGNet’s improvements are not only evident across different semantic categories but also extend to various generative methods, including multiple GAN-based and diffusion-based models. This cross-method generalization emphasizes SAGNet’s versatility and effectiveness in diverse generative scenarios. Overall, our method represents a significant advancement in deepfake detection, particularly in realistic situations where the training data is limited. The code is released at https://github.com/rstao-bjtu/SAGNet/.