XLXin Liao

Xin Liao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xin Liao has a total of 186 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Cross-Modal Inconsistent Information-Based Network for Fake News Detection

    by Aohan Li, Jiaxin Chen, Dengyong Zhang, Yuling Liu, Yihui Luo, Xin Liao

  • Towards Imperceptible Color JPEG Image Hiding: Multi-Range Representations-Driven Adversarial Stego Generation

    by Junxue Yang, Xin Liao, Weixuan Tang, Jianhua Yang, Zhen Xia, Zheng Qin

    Image hiding fully explores the hidden potential of deep learning-based models, aiming to conceal image-level messages within cover images and reveal them from stego images to achieve covert communication. Although image hiding has made significant progress, achieving imperceptible color JPEG image hiding remains challenging. Existing hiding schemes are easily detected by the naked eyes or steganalyzers due to the cover type confined to the spatial domain, single-range feature extraction and attacks, and insufficient loss constraints. In this paper, we propose a multi-range representations-driven adversarial stego generation framework called MRAG for color JPEG image hiding. The proposed MRAG can address the aforementioned shortcomings within a unified framework, enabling steganalysis imperceptibility in color JPEG image hiding while ensuring secret restorability and visual imperceptibility. Specifically, MRAG integrates the local-range characteristic of the convolution and the global-range modeling of the transformer. This design stems from the fact that steganalyzers typically combine local-range and global-range information to better capture hidden traces. Meanwhile, we introduce a loss function, termed the features angle-norm disentanglement loss, to launch multi-range representations-driven feature-level adversarial attacks. It computes the adversarial loss between covers and stegos based on the surrogate steganalyzer’s classified features, i.e., the features before the last fully connected layer. Under the dual constraints of features angle and norm, MRAG can delicately encode the concatenation of cover and secret into subtle adversarial perturbations from local and global ranges relevant to steganalysis. Therefore, the resulting stego can achieve visual and steganalysis imperceptibility. Moreover, coarse-grained and fine-grained frequency decomposition operations are devised to transform the input, introducing multi-grained frequency information. Extensive experiments demonstrate that MRAG can achieve state-of-the-art performance.


  • One-Identity-One-Key: Region-aware Watermark for Proactive Deepfake Detection and Robust Source Tracing

    by Ziyuan He, Zhiqing Guo, Liejun Wang, Xiaoming Tao, Xin Liao

    Proactive forensic methods based on watermarking have attracted increasing attention as an effective paradigm for deepfake detection and source tracing. However, the existing methods still have shortcomings in encryption security, robustness and detection performance when dealing with complex forgery. In this paper, we propose a region-aware watermarking based proactive deepfake detection framework named Segfacemark. Building on global watermark embedding, this method explicitly models the sensitivity of various semantic facial regions to tampering. By employing region-wise partitioning and redundant embedding, the framework strengthens the protection of key facial areas, thereby comprehensively enhancing watermark robustness. In addition, the proposed framework employs a dynamic encryption mechanism that derives personalized keys from identity features to encrypt structural features, thereby realizing a “one-identity–one-key” watermark generation strategy and significantly enhancing system security and robustness against forgery. In the detection stage, the dual verification mechanism of identity decryption consistency and global region-aware watermark consistency not only improves detection accuracy but also enables forgery type identification, and further enhances the interpretability of deepfake detection results through region-aware watermarks. Experimental results show that the proposed method achieves high accuracy and robustness in deepfake detection, while preserving visual fidelity. The code will be released at: https://github.com/vpsg-research/Segfacemark.


  • Universal Adversarial Watermarking for Text Image Protection Via Template-Based Underpainting

    by Fangjun Yan, Yutong Huang, Li Dong, Jiacheng Deng, Qiuping Jiang, Zhibo Wang, Xin Liao

    Text images are images that contain textual content. They are vulnerable to content piracy through Optical Character Recognition (OCR) and unauthorized distribution. Existing methods based solely on adversarial examples or digital watermarking are insufficient to address both threats effectively. In this work, we propose Universal Adversarial Watermarking (UAW), a dual protection that misleads OCR systems and enables watermarking for traceability simultaneously. Specifically, we first generate two templates for representing watermark bits while attaining adversarial capability against OCR. Then, the watermark message is encoded via structured tiling of the bit templates into the underpainting of text images. Finally, the embedded watermark can be reliably extracted with the aid of watermark block synchronization and a majority voting mechanism. Experimental results demonstrate the effectiveness of the proposed method in terms of adversarial capability and watermarking functionality. We also validate the transferability of UAW across various font sizes, colors and languages, and evaluate the practical usage through real-world applications. The code is publicly available at https://github.com/yfjn/UAW.

  • FALCON-Net: Feature Aggregation of Local Patterns for AI-Generated Image Detection

    by Dengyong Zhang, Miao Hu, Jiaxin Chen, Changsheng Chen, Jin Wang, Yun Song, Gaobo Yang, Xin Liao, Xiangling Ding

    With the rapid development of generative models, the visual quality of generated images has become almost indistinguishable from real images, which poses a huge challenge to content authenticity verification. A key limitation of existing detectors is their reliance on model-specific cues, resulting in poor generalization to unseen models. Based on the observation of local differences in the generated images, we found that the generated images lack device-specific sensor noise and unnatural pixel intensity variations caused by the oversimplified generation process. These discrepancies provide important forensic cues for distinguishing between real and generated images. We propose the Feature Aggregation for Localized Context and Noise Network (FALCON-Net), which leverages these discrepancies to enhance detection capabilities. FALCON-Net integrates two complementary modules to enhance detection capabilities: the Intrinsic Noise Pattern Isolation (INP) module isolates device-specific noise patterns by analyzing high-frequency features in the frequency domain, while the Local Variation Pattern (LVP) module models the complex relationships between local pixels to capture directional intensity variations and reveal unnatural regularities in generated images. By combining these sensor-level and local structural cues, FALCON-Net identifies fundamental generative inconsistencies, ensuring robustness to post-processing and strong generalization to unseen models. Extensive experimental results show that FALCON-Net achieves the state-of-the-art performance in detecting generated images and shows good generalization ability to unseen generative models. The code is available at https://github.com/humiaomiaohaha/FALCON-Net.


  • Prototype Memory-based Neighboring Feature Fusion Network for Image Manipulation Localization

    by Songlin Li, Zhiqing Guo, Changtao Miao, Wenzhong Yang, Liejun Wang, Gaobo Yang, Xin Liao

    Image manipulation localization (IML) aims to segment manipulated regions in suspicious images. However, most existing methods rely solely on intrinsic features extracted from the input image and passively model local or global inconsistencies, making it difficult to accurately delineate manipulated regions with ambiguous boundaries. To address these challenges, we propose a prototype memory-based neighboring feature fusion network (PNF-Net), which is inspired by a biological memory mechanism. PNF-Net simulates selective preference by learning manipulation-trace prototypes as memory priors, thereby guiding representation learning toward consistent and discriminative manipulation cues. Specifically, we propose a memory-guided localization module (MLM) that models the consistencies and anomalies between manipulated regions and the background as memory priors, enabling precise localization. We then propose a neighboring feature interaction module (NFIM) that preserves fine-grained details from neighboring shallow features, enhances global semantics from neighboring deep features, and effectively fuses them. Finally, a verification fusion module (VFM) is designed to enrich contextual semantics and improve the completeness and accuracy of localization results. Extensive experiments on multiple benchmark datasets show that our PNF-Net outperforms most state-of-the-art IML models. Our code is available on https://github.com/vpsg-research/PNF-Net.


  • Multi-Dimensional Histogram Modification Framework for Reversible Data Hiding in JPEG Images

    by Kaiyue Hou, Cheng Zeng, Xiaoyi Zhou, Dahao Fu, Xin Liao

    Reversible data hiding in JPEG images is critical for secure multimedia applications, while, existing histogram modification schemes are confined to fixed 1D or 2D dimensions. These methods fail to adapt to the characteristics of cover images and the demands of embedded data, resulting in suboptimal trade-offs among embedding capacity, image quality, and file size. To address these issues, this study proposes a Multi-Dimensional Histogram Modification Framework that advances histograms from "fixed dimension" to "variable dimension" and extends them to high-dimensional structures. Our key contributions are as follows: first, we propose an adaptive dimension selection strategy that dynamically determines the optimal histogram dimension by evaluating the capacity and distortion for each cover image and embedding task; second, we develop a high-dimensional histogram construction method that combines AC coefficients with absolute values of 1 and 2 at the same frequency to enhance the utilization of coefficient correlation; third, we design an optimized mapping algorithm that searches for the optimal mapping matrix to minimize both distortion and file expansion. Experimental results show that the proposed method outperforms existing 1D and 2D histogram modification schemes. On average, it increases the embedding capacity by 5000 bits, improves the image quality by 0.2 dB, and reduces the file size by 4000 bits.


  • Open Access

    NiMark: A Non-intrusive Watermarking Framework against Screen-shooting Attacks

    by Yufeng Wu, Xin Liao, Baowei Wang, Han Fang, Xiaoshuai Wu, Guiling Wang

    Unauthorized screen-shooting poses a critical data leakage risk. Resisting screen-shooting attacks typically requires high-strength watermark embedding, inevitably degrading the cover image. To resolve the robustness-fidelity conflict, non-intrusive watermarking has emerged as a solution by constructing logical verification keys without altering the original content. However, existing non-intrusive schemes lack the capacity to withstand screen-shooting noise. While deep learning offers a potential remedy, we observe that directly applying it leads to a previously underexplored failure mode, the Structural Shortcut: networks tend to learn trivial identity mappings and neglect the image-watermark binding. Furthermore, even when logical binding is enforced, standard training strategies cannot fully bridge the noise gap, yielding suboptimal robustness against physical distortions. In this paper, we propose NiMark, an end-to-end framework addressing these challenges. First, to eliminate the structural shortcut, we introduce the Sigmoid-Gated XOR (SG-XOR) estimator to enable gradient propagation for the logical operation, effectively enforcing rigid image-watermark binding. Second, to overcome the robustness bottleneck, we devise a two-stage training strategy integrating a restorer to bridge the domain gap caused by screen-shooting noise. Experiments demonstrate that NiMark consistently outperforms representative state-of-the-art methods against both digital attacks and screen-shooting noise, while maintaining zero visual distortion.

  • Open Access

    DDNet: A Dual-Stream Graph Learning and Disentanglement Framework for Temporal Forgery Localization

    by Boyang Zhao, Xin Liao, Jiaxin Chen, Xiaoshuai Wu, Yufeng Wu

    The rapid evolution of AIGC technology enables misleading viewers by tampering mere small segments within a video, rendering video-level detection inaccurate and unpersuasive. Consequently, temporal forgery localization (TFL), which aims to precisely pinpoint tampered segments, becomes critical. However, existing methods are often constrained by \emph{local view}, failing to capture global anomalies. To address this, we propose a \underline{d}ual-stream graph learning and \underline{d}isentanglement framework for temporal forgery localization (DDNet). By coordinating a \emph{Temporal Distance Stream} for local artifacts and a \emph{Semantic Content Stream} for long-range connections, DDNet prevents global cues from being drowned out by local smoothness. Furthermore, we introduce Trace Disentanglement and Adaptation (TDA) to isolate generic forgery fingerprints, alongside Cross-Level Feature Embedding (CLFE) to construct a robust feature foundation via deep fusion of hierarchical features. Experiments on ForgeryNet and TVIL benchmarks demonstrate that our method outperforms state-of-the-art approaches by approximately 9\% in AP@0.95, with significant improvements in cross-domain robustness.