Imagen de Portada

Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Yilong, Li, Songze
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Robust Protective Perturbation against DeepFake Face Swapping
por: Yao, Hengyang, et al.
Publicado: (2025)

AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing
por: Hong, Ziming, et al.
Publicado: (2025)

IU: Imperceptible Universal Backdoor Attack
por: Lin, Hsin, et al.
Publicado: (2026)

Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation
por: He, Yuhao, et al.
Publicado: (2025)

Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attack
por: Wang, Yinggui, et al.
Publicado: (2024)

Transparency Attacks: How Imperceptible Image Layers Can Fool AI Perception
por: McKee, Forrest, et al.
Publicado: (2024)

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models
por: Xu, Jingyao, et al.
Publicado: (2024)

How does Watermarking Affect Visual Language Models in Document Understanding?
por: Xu, Chunxue, et al.
Publicado: (2025)

DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
por: Wang, Hanrui, et al.
Publicado: (2025)

Leveraging Diffusion For Strong and High Quality Face Morphing Attacks
por: Blasingame, Zander W., et al.
Publicado: (2023)

IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning
por: Wang, Jiayao, et al.
Publicado: (2025)

Boosting Adversarial Transferability via Residual Perturbation Attack
por: Peng, Jinjia, et al.
Publicado: (2025)

Deep Learning with Data Privacy via Residual Perturbation
por: Tao, Wenqi, et al.
Publicado: (2024)

SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
por: Zhang, Xin, et al.
Publicado: (2026)

EditTrack: Detecting and Attributing AI-assisted Image Editing
por: Jiang, Zhengyuan, et al.
Publicado: (2025)

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
por: Chen, Hao, et al.
Publicado: (2025)

Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics
por: Li, Shuai, et al.
Publicado: (2024)

A Machine Learning-Based Secure Face Verification Scheme and Its Applications to Digital Surveillance
por: Wang, Huan-Chih, et al.
Publicado: (2024)

Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations
por: Qian, Jiachen, et al.
Publicado: (2026)

Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection
por: Cui, Xinjie, et al.
Publicado: (2024)

Does CLIP Know My Face?
por: Hintersdorf, Dominik, et al.
Publicado: (2022)

CipherFace: A Fully Homomorphic Encryption-Driven Framework for Secure Cloud-Based Facial Recognition
por: Serengil, Sefik, et al.
Publicado: (2025)

Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks using Hyperparameter Tuning
por: Zimmer, Pascal, et al.
Publicado: (2025)

Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples
por: Yilmaz, Eda, et al.
Publicado: (2024)

DiffBreak: Is Diffusion-Based Purification Robust?
por: Kassis, Andre, et al.
Publicado: (2024)

Beyond Full Poisoning: Effective Availability Attacks with Partial Perturbation
por: Zhe, Yu, et al.
Publicado: (2024)

Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
por: Ying, Chengyang, et al.
Publicado: (2022)

Reliable Disentanglement Multi-view Learning Against View Adversarial Attacks
por: Wang, Xuyang, et al.
Publicado: (2025)

Learning Counterfactually Decoupled Attention for Open-World Model Attribution
por: Zheng, Yu, et al.
Publicado: (2025)

Robust Classification via a Single Diffusion Model
por: Chen, Huanran, et al.
Publicado: (2023)

Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
por: Singh, Naman Deep, et al.
Publicado: (2024)

Identifying Physically Realizable Triggers for Backdoored Face Recognition Networks
por: Raj, Ankita, et al.
Publicado: (2025)

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks
por: Xiao, Yaxin, et al.
Publicado: (2025)

Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
por: Shpilevskiy, Frederick, et al.
Publicado: (2025)

SaFL: Sybil-aware Federated Learning with Application to Face Recognition
por: Ghafourian, Mahdi, et al.
Publicado: (2023)

Enhancing Remote Adversarial Patch Attacks on Face Detectors with Tiling and Scaling
por: Okano, Masora, et al.
Publicado: (2024)

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models
por: Li, Wenda, et al.
Publicado: (2024)

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
por: Yang, Sheng, et al.
Publicado: (2024)

Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation
por: Liu, Bochao, et al.
Publicado: (2024)

Latent Code Augmentation Based on Stable Diffusion for Data-free Substitute Attacks
por: Shao, Mingwen, et al.
Publicado: (2023)