Cover Image

Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Yuhao, Tian, Jinyu, Wu, Haiwei, Li, Jianqing
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption
by: Jeon, Joonsung, et al.
Published: (2025)

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
by: He, Yuhao, et al.
Published: (2024)

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

Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing
by: Huang, Yilong, et al.
Published: (2026)

Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
by: Khine, Ei Hmue, et al.
Published: (2026)

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

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

MedBN: Robust Test-Time Adaptation against Malicious Test Samples
by: Park, Hyejin, et al.
Published: (2024)

iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself
by: Bian, Yuhao, et al.
Published: (2024)

Trusted Video Inpainting Localization via Deep Attentive Noise Learning
by: Lou, Zijie, et al.
Published: (2024)

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

Video Inpainting Localization with Contrastive Learning
by: Lou, Zijie, et al.
Published: (2024)

Closing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks
by: Zimmer, Pascal, et al.
Published: (2023)

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

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

AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization
by: Li, Jiyao, et al.
Published: (2024)

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
by: Jia, Yuqi, et al.
Published: (2024)

Efficient Malicious UAV Detection Using Autoencoder-TSMamba Integration
by: Akhtarshenas, Azim, et al.
Published: (2025)

TarPro: Targeted Protection against Malicious Image Editing
by: Shen, Kaixin, et al.
Published: (2025)

Disrupting Style Mimicry Attacks on Video Imagery
by: Passananti, Josephine, et al.
Published: (2024)

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

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

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

Improving Adversarial Training using Vulnerability-Aware Perturbation Budget
by: Fakorede, Olukorede, et al.
Published: (2024)

DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
by: Cui, Yingqian, et al.
Published: (2023)

SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented Training
by: Zhang, Lu, et al.
Published: (2024)

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

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

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

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

Detecting Malicious Concepts without Image Generation in AI-Generated Content (AIGC)
by: Xu, Kun, et al.
Published: (2025)

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
by: Fan, Mingyuan, et al.
Published: (2024)

Adversarial Training in Low-Label Regimes with Margin-Based Interpolation
by: Ye, Tian, et al.
Published: (2024)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
by: Fang, Hao, et al.
Published: (2024)

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

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

Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement
by: Yu, Daiwei, et al.
Published: (2024)

Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models
by: Ahn, Jaesin, et al.
Published: (2025)

Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection
by: Zhu, Delong, et al.
Published: (2024)

CP-Guard+: A New Paradigm for Malicious Agent Detection and Defense in Collaborative Perception
by: Hu, Senkang, et al.
Published: (2025)