Weiming Zhang

40

Papers

452

Total Citations

Papers (40)

OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers

A Closer Look at Machine Unlearning for Large Language Models

FaceRSA: RSA-Aware Facial Identity Cryptography Framework

Data-Free Hard-Label Robustness Stealing Attack

TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity

CoSDA: Enhancing the Robustness of Inversion-based Generative Image Watermarking Framework

RoPaSS: Robust Watermarking for Partial Screen-Shooting Scenarios

Provably Secure Image Robust Steganography via Cross-modal Error Correction

MuST: Robust Image Watermarking for Multi-Source Tracing

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA

Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation

Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View

LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks

Robust Superpixel-Guided Attentional Adversarial Attack

Self-Robust 3D Point Recognition via Gather-Vector Guidance

Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain

Improved Image Matting via Real-Time User Clicks and Uncertainty Estimation

Multi-Attentional Deepfake Detection

CSWin Transformer: A General Vision Transformer Backbone With Cross-Shaped Windows

Shape-Invariant 3D Adversarial Point Clouds

HairCLIP: Design Your Hair by Text and Reference Image

Protecting Celebrities From DeepFake With Identity Consistency Transformer

Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection

Diversity-Aware Meta Visual Prompting

MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining

DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense

Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once

CFCG: Semi-Supervised Semantic Segmentation via Cross-Fusion and Contour Guidance Supervision

Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting

HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending

Bootstrapped Masked Autoencoders for Vision BERT Pretraining

Graph-Embedded Structure-Aware Perceptual Hashing for Neural Network Protection and Piracy Detection

PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation

Deciphering Cross-Modal Alignment in Large Vision-Language Models via Modality Integration Rate

SynTag: Enhancing the Geometric Robustness of Inversion-based Generative Image Watermarking

LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation

GreedyFool: Distortion-Aware Sparse Adversarial Attack

Passport-aware Normalization for Deep Model Protection