Zhaoxia Yin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhaoxia Yin has a total of 139 co-authors. Here are the top co-authors by number of shared publications:
- Xinpeng Zhang
Fudan University, Shanghai, China
14 shared publications Bin Luo
9 shared publications- Bin Luo
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
8 shared publications Xinpeng Zhang
Fudan University
7 shared publications- Hang Su
Tsinghua University
6 shared publications Jin Tang
Anhui Univ, Sch Comp Sci & Technol, Anhui Prov Key Lab Multimodal Cognit Computat, Hefei 230601, Anhui, Peoples R China
6 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 476-485
Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 476-485
Open AccessTex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
- Open Access
- 16 September 2026
- Published by Springer Nature in Visual Intelligence
- Vol. 4 (1) , 27
Adversarial attacks on medical hyperspectral imaging exploiting spectral-spatial dependencies and multiscale features
Medical hyperspectral imaging (MHSI) has demonstrated considerable promise in disease diagnosis by capturing spectral-spatial information of tissues. While deep learning has substantially improved MHSI classification accuracy, its robustness remains limited due to the well-known trade-off between accuracy and robustness in deep neural networks (DNNs). This issue is particularly critical in MHSI, where reliable prediction depends on local tissue relationships and multiscale spectral-spatial structures. A practical way to improve robustness is to identify the most unstable adversarial examples and incorporate them into adversarial training. However, existing attack methods do not sufficiently exploit these MHSI-specific properties, leading to suboptimal attack effectiveness and limited value for robustness enhancement. To address this gap, we propose a structured adversarial attack framework for MHSI that progressively models its local spectral-spatial dependencies and multiscale hierarchical representations. The proposed method generates anatomically consistent perturbations by modeling neighborhood dependencies and hierarchical spectral-spatial features. Experiments on the hyperspectral human brain image (the Brain) dataset and the multidimensional choledoch (MDC) dataset show that our method degrades lesion-related classification performance in critical tumor regions more effectively than existing baselines while maintaining low perturbation magnitude. These results reveal a clinically relevant robustness weakness in current MHSI models and provide stronger adversarial samples for developing targeted defense strategies.
- 16 September 2026
- Published by Springer Nature in Visual Intelligence
- Vol. 4 (1) , 27
Open AccessAdversarial attacks on medical hyperspectral imaging exploiting spectral-spatial dependencies and multiscale features
Medical hyperspectral imaging (MHSI) has demonstrated considerable promise in disease diagnosis by capturing spectral-spatial information of tissues. While deep learning has substantially improved MHSI classification accuracy, its robustness remains limited due to the well-known trade-off between accuracy and robustness in deep neural networks (DNNs). This issue is particularly critical in MHSI, where reliable prediction depends on local tissue relationships and multiscale spectral-spatial structures. A practical way to improve robustness is to identify the most unstable adversarial examples and incorporate them into adversarial training. However, existing attack methods do not sufficiently exploit these MHSI-specific properties, leading to suboptimal attack effectiveness and limited value for robustness enhancement. To address this gap, we propose a structured adversarial attack framework for MHSI that progressively models its local spectral-spatial dependencies and multiscale hierarchical representations. The proposed method generates anatomically consistent perturbations by modeling neighborhood dependencies and hierarchical spectral-spatial features. Experiments on the hyperspectral human brain image (the Brain) dataset and the multidimensional choledoch (MDC) dataset show that our method degrades lesion-related classification performance in critical tumor regions more effectively than existing baselines while maintaining low perturbation magnitude. These results reveal a clinically relevant robustness weakness in current MHSI models and provide stronger adversarial samples for developing targeted defense strategies.
- Open Access
VocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter Injection
Generated speech achieves human-level naturalness but escalates security risks of misuse. However, existing watermarking methods fail to reconcile fidelity with robustness, as they rely either on simple superposition in the noise space or on intrusive alterations to model weights. To bridge this gap, we propose VocBulwark, an additional-parameter injection framework that freezes generative model parameters to preserve perceptual quality. Specifically, we design a Temporal Adapter to deeply entangle watermarks with acoustic attributes, synergizing with a Coarse-to-Fine Gated Extractor to resist advanced attacks. Furthermore, we develop an Accuracy-Guided Optimization Curriculum that dynamically orchestrates gradient flow to resolve the optimization conflict between fidelity and robustness. Comprehensive experiments demonstrate that VocBulwark achieves high-capacity and high-fidelity watermarking, offering robust defense against complex practical scenarios, with resilience to Codec regenerations and variable-length manipulations.
Open AccessVocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter Injection
Generated speech achieves human-level naturalness but escalates security risks of misuse. However, existing watermarking methods fail to reconcile fidelity with robustness, as they rely either on simple superposition in the noise space or on intrusive alterations to model weights. To bridge this gap, we propose VocBulwark, an additional-parameter injection framework that freezes generative model parameters to preserve perceptual quality. Specifically, we design a Temporal Adapter to deeply entangle watermarks with acoustic attributes, synergizing with a Coarse-to-Fine Gated Extractor to resist advanced attacks. Furthermore, we develop an Accuracy-Guided Optimization Curriculum that dynamically orchestrates gradient flow to resolve the optimization conflict between fidelity and robustness. Comprehensive experiments demonstrate that VocBulwark achieves high-capacity and high-fidelity watermarking, offering robust defense against complex practical scenarios, with resilience to Codec regenerations and variable-length manipulations.
- Open Access
Robust Reversible Watermarking in Encrypted Images Based on Dual-MSBs Spiral Embedding
Robust reversible watermarking in encrypted images (RRWEI) faces an inherent challenge in simultaneously achieving robustness, reversibility, and content privacy under severely constrained embedding capacity. Existing RRWEI schemes often exhibit limited robustness against noise, lossy compression, and cropping attacks due to insufficient redundancy in the encrypted domain. To address this challenge, this paper proposes a novel RRWEI framework that couples dual most significant bit-plane (dual-MSBs) embedding with spatial redundancy and error-correcting coding. By compressing prediction-error bit-planes, sufficient embedding space and auxiliary information for lossless reconstruction are reserved. The dual-MSBs are further reorganized using a spiral embedding strategy to distribute multiple redundant watermark copies across spatially dispersed regions, enhancing robustness against both noise and spatial loss.Experimental results on standard test images demonstrate that the proposed method consistently outperforms under evaluated settings robustness against Gaussian noise, JPEG compression, and diverse cropping attacks, while maintaining perfect reversibility and high embedding capacity. Compared with state-of-the-art RRWEI schemes, the proposed framework achieves substantially lower bit-error rates and more stable performance under a wide range of attack scenarios.
Open AccessRobust Reversible Watermarking in Encrypted Images Based on Dual-MSBs Spiral Embedding
Robust reversible watermarking in encrypted images (RRWEI) faces an inherent challenge in simultaneously achieving robustness, reversibility, and content privacy under severely constrained embedding capacity. Existing RRWEI schemes often exhibit limited robustness against noise, lossy compression, and cropping attacks due to insufficient redundancy in the encrypted domain. To address this challenge, this paper proposes a novel RRWEI framework that couples dual most significant bit-plane (dual-MSBs) embedding with spatial redundancy and error-correcting coding. By compressing prediction-error bit-planes, sufficient embedding space and auxiliary information for lossless reconstruction are reserved. The dual-MSBs are further reorganized using a spiral embedding strategy to distribute multiple redundant watermark copies across spatially dispersed regions, enhancing robustness against both noise and spatial loss.Experimental results on standard test images demonstrate that the proposed method consistently outperforms under evaluated settings robustness against Gaussian noise, JPEG compression, and diverse cropping attacks, while maintaining perfect reversibility and high embedding capacity. Compared with state-of-the-art RRWEI schemes, the proposed framework achieves substantially lower bit-error rates and more stable performance under a wide range of attack scenarios.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 5000-5014
Generative Image Steganography With Minimum-Distance Guidance
Image steganography conceals secret data within a digital image while preserving its innocent appearance. The advent of artificial intelligence generative models has given rise to a new paradigm known as generative image steganography, which hides secret data directly into the image generation process. However, existing generative image steganographic methods are typically only applicable to unquantized stego images, severely limiting their practicality in real-world scenarios. To address this limitation, we propose a generative image steganography with minimum-distance guidance based on a diffusion model, called MDStega. During the hiding phase, MDStega designs a secret data-driven residual image sampling mechanism, which establishes a dynamic mapping relationship between discrete secret data and continuous probability distributions, strictly preserving the distribution consistency between stego images and normally generated images. During the extraction phase, the minimum-distance guidance rule effectively suppresses the interference caused by stego image quantization on the extraction accuracy of secret data. Furthermore, MDStega does not require fine-tuning pre-trained models or training additional models, which significantly reduces computational overhead and training time. Experimental results demonstrate that MDStega is superior to state-of-the-art methods by not only ensuring secure concealment at 3 bits per pixel (bpp) in PNG format but also achieving a recovery accuracy of up to 99%, demonstrating strong practical potential.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 5000-5014
Generative Image Steganography With Minimum-Distance Guidance
Image steganography conceals secret data within a digital image while preserving its innocent appearance. The advent of artificial intelligence generative models has given rise to a new paradigm known as generative image steganography, which hides secret data directly into the image generation process. However, existing generative image steganographic methods are typically only applicable to unquantized stego images, severely limiting their practicality in real-world scenarios. To address this limitation, we propose a generative image steganography with minimum-distance guidance based on a diffusion model, called MDStega. During the hiding phase, MDStega designs a secret data-driven residual image sampling mechanism, which establishes a dynamic mapping relationship between discrete secret data and continuous probability distributions, strictly preserving the distribution consistency between stego images and normally generated images. During the extraction phase, the minimum-distance guidance rule effectively suppresses the interference caused by stego image quantization on the extraction accuracy of secret data. Furthermore, MDStega does not require fine-tuning pre-trained models or training additional models, which significantly reduces computational overhead and training time. Experimental results demonstrate that MDStega is superior to state-of-the-art methods by not only ensuring secure concealment at 3 bits per pixel (bpp) in PNG format but also achieving a recovery accuracy of up to 99%, demonstrating strong practical potential.
- Open Access
Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attacks
As vision-language models (VLMs) become widely adopted, VLM-based attribute inference attacks have emerged as a serious privacy concern, enabling adversaries to infer private attributes from images shared on social media. This escalating threat calls for dedicated protection methods to safeguard user privacy. However, existing methods often degrade the visual quality of images or interfere with vision-based functions on social media, thereby failing to achieve a desirable balance between privacy protection and user experience. To address this challenge, we propose a novel protection method that jointly optimizes privacy suppression and utility preservation under a visual consistency constraint. While our method is conceptually effective, fair comparisons between methods remain challenging due to the lack of publicly available evaluation datasets. To fill this gap, we introduce VPI-COCO, a publicly available benchmark comprising 522 images with hierarchically structured privacy questions and corresponding non-private counterparts, enabling fine-grained and joint evaluation of protection methods in terms of privacy preservation and user experience. Building upon this benchmark, experiments on multiple VLMs demonstrate that our method effectively reduces PAR below 25%, keeps NPAR above 88%, maintains high visual consistency, and generalizes well to unseen and paraphrased privacy questions, demonstrating its strong practical applicability for real-world VLM deployments.
Open AccessWho Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attacks
As vision-language models (VLMs) become widely adopted, VLM-based attribute inference attacks have emerged as a serious privacy concern, enabling adversaries to infer private attributes from images shared on social media. This escalating threat calls for dedicated protection methods to safeguard user privacy. However, existing methods often degrade the visual quality of images or interfere with vision-based functions on social media, thereby failing to achieve a desirable balance between privacy protection and user experience. To address this challenge, we propose a novel protection method that jointly optimizes privacy suppression and utility preservation under a visual consistency constraint. While our method is conceptually effective, fair comparisons between methods remain challenging due to the lack of publicly available evaluation datasets. To fill this gap, we introduce VPI-COCO, a publicly available benchmark comprising 522 images with hierarchically structured privacy questions and corresponding non-private counterparts, enabling fine-grained and joint evaluation of protection methods in terms of privacy preservation and user experience. Building upon this benchmark, experiments on multiple VLMs demonstrate that our method effectively reduces PAR below 25%, keeps NPAR above 88%, maintains high visual consistency, and generalizes well to unseen and paraphrased privacy questions, demonstrating its strong practical applicability for real-world VLM deployments.
- Open Access
SAIDO: Generalizable Detection of AI-Generated Images via Scene-Aware and Importance-Guided Dynamic Optimization in Continual Learning
The widespread misuse of image generation technologies has raised security concerns, driving the development of AI-generated image detection methods. However, generalization has become a key challenge and open problem: existing approaches struggle to adapt to emerging generative methods and content types in real-world scenarios. To address this issue, we propose a Scene-Aware and Importance-Guided Dynamic Optimization detection framework with continual learning (SAIDO). Specifically, we design Scene-Awareness-Based Expert Module (SAEM) that dynamically identifies and incorporates new scenes using VLLMs. For each scene, independent expert modules are dynamically allocated, enabling the framework to capture scene-specific forgery features better and enhance cross-scene generalization. To mitigate catastrophic forgetting when learning from multiple image generative methods, we introduce Importance-Guided Dynamic Optimization Mechanism (IDOM), which optimizes each neuron through an importance-guided gradient projection strategy, thereby achieving an effective balance between model plasticity and stability. Extensive experiments on continual learning tasks demonstrate that our method outperforms the current SOTA method in both stability and plasticity, achieving 44.22\% and 40.57\% relative reductions in average detection error rate and forgetting rate, respectively. On open-world datasets, it improves the average detection accuracy by 9.47\% compared to the current SOTA method.
Open AccessSAIDO: Generalizable Detection of AI-Generated Images via Scene-Aware and Importance-Guided Dynamic Optimization in Continual Learning
The widespread misuse of image generation technologies has raised security concerns, driving the development of AI-generated image detection methods. However, generalization has become a key challenge and open problem: existing approaches struggle to adapt to emerging generative methods and content types in real-world scenarios. To address this issue, we propose a Scene-Aware and Importance-Guided Dynamic Optimization detection framework with continual learning (SAIDO). Specifically, we design Scene-Awareness-Based Expert Module (SAEM) that dynamically identifies and incorporates new scenes using VLLMs. For each scene, independent expert modules are dynamically allocated, enabling the framework to capture scene-specific forgery features better and enhance cross-scene generalization. To mitigate catastrophic forgetting when learning from multiple image generative methods, we introduce Importance-Guided Dynamic Optimization Mechanism (IDOM), which optimizes each neuron through an importance-guided gradient projection strategy, thereby achieving an effective balance between model plasticity and stability. Extensive experiments on continual learning tasks demonstrate that our method outperforms the current SOTA method in both stability and plasticity, achieving 44.22\% and 40.57\% relative reductions in average detection error rate and forgetting rate, respectively. On open-world datasets, it improves the average detection accuracy by 9.47\% compared to the current SOTA method.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11590-11599
Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11590-11599
Open AccessProtecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
- 24 July 2025
- Published by Elsevier in Neurocomputing
- Vol. 652
Efficient and transferable reversible adversarial attacks utilizing YUV color space
- 24 July 2025
- Published by Elsevier in Neurocomputing
- Vol. 652
Efficient and transferable reversible adversarial attacks utilizing YUV color space
- 18 May 2025
- Published by Elsevier in Signal Processing
- Vol. 238
A survey of fragile model watermarking
- 18 May 2025
- Published by Elsevier in Signal Processing
- Vol. 238
A survey of fragile model watermarking