Xiao Yang

papers

1,572

total citations

papers (22)

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

ICML 2024arXiv

113

citations

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

CVPR 2022arXiv

107

citations

Towards Face Encryption by Generating Adversarial Identity Masks

ICCV 2021arXiv

citations

Robust Classification via a Single Diffusion Model

ICML 2024arXiv

citations

LiBRe: A Practical Bayesian Approach to Adversarial Detection

CVPR 2021arXiv

citations

Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition

CVPR 2023arXiv

citations

Shifted Diffusion for Text-to-Image Generation

CVPR 2023arXiv

citations

Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks

ECCV 2022arXiv

citations

Design and Interpretation of Universal Adversarial Patches in Face Detection

ECCV 2020arXiv

citations

Unsupervised Part Segmentation Through Disentangling Appearance and Shape

CVPR 2021arXiv

citations

Towards Transferable Targeted 3D Adversarial Attack in the Physical World

CVPR 2024arXiv

citations

Accumulative Poisoning Attacks on Real-time Data

NEURIPS 2021arXiv

citations

PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters

CVPR 2023arXiv

citations

A Generalizable Anomaly Detection Method in Dynamic Graphs

AAAI 2025arXiv

citations

Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos

ICCV 2023arXiv

citations

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

ICML 2024arXiv

citations

Benchmarking Adversarial Robustness on Image Classification

CVPR 2020

citations

WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios

NEURIPS 2025arXiv

citations

Xiao Yang

papers (22)

On Evaluating Adversarial Robustness of Large Vision-Language Models

Boosting Adversarial Training with Hypersphere Embedding

Benchmarking Robustness of 3D Object Detection to Common Corruptions

Black-Box Detection of Backdoor Attacks With Limited Information and Data

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

Towards Face Encryption by Generating Adversarial Identity Masks

Robust Classification via a Single Diffusion Model

LiBRe: A Practical Bayesian Approach to Adversarial Detection

Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition

Shifted Diffusion for Text-to-Image Generation

Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks

Design and Interpretation of Universal Adversarial Patches in Face Detection

Unsupervised Part Segmentation Through Disentangling Appearance and Shape

Towards Transferable Targeted 3D Adversarial Attack in the Physical World

Accumulative Poisoning Attacks on Real-time Data

PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters

A Generalizable Anomaly Detection Method in Dynamic Graphs

Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

Benchmarking Adversarial Robustness on Image Classification

WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios

papers (22)

On Evaluating Adversarial Robustness of Large Vision-Language Models

Boosting Adversarial Training with Hypersphere Embedding

Benchmarking Robustness of 3D Object Detection to Common Corruptions

Black-Box Detection of Backdoor Attacks With Limited Information and Data

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

Towards Face Encryption by Generating Adversarial Identity Masks

Robust Classification via a Single Diffusion Model

LiBRe: A Practical Bayesian Approach to Adversarial Detection

Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition

Shifted Diffusion for Text-to-Image Generation

Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks

Design and Interpretation of Universal Adversarial Patches in Face Detection

Unsupervised Part Segmentation Through Disentangling Appearance and Shape

Towards Transferable Targeted 3D Adversarial Attack in the Physical World

Accumulative Poisoning Attacks on Real-time Data

PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters

A Generalizable Anomaly Detection Method in Dynamic Graphs

Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

Benchmarking Adversarial Robustness on Image Classification

WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios