Copertina

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Jingyao, Lu, Yuetong, Li, Yandong, Lu, Siyang, Wang, Dongdong, Wei, Xiang
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Diffusion-Guided Adversarial Perturbation Injection for Generalizable Defense Against Facial Manipulations
di: Li, Yue, et al.
Pubblicazione: (2026)

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

StyleFool: Fooling Video Classification Systems via Style Transfer
di: Cao, Yuxin, et al.
Pubblicazione: (2022)

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

Attacking Transformers with Feature Diversity Adversarial Perturbation
di: Gao, Chenxing, et al.
Pubblicazione: (2024)

Less Is More: Sparse and Cooperative Perturbation for Point Cloud Attacks
di: Tang, Keke, et al.
Pubblicazione: (2025)

LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
di: Cao, Yuxin, et al.
Pubblicazione: (2023)

Erasing Radio Frequency Fingerprints via Active Adversarial Perturbation
di: Lu, Zhaoyi, et al.
Pubblicazione: (2024)

Privacy Loss of Noise Perturbation via Concentration Analysis of A Product Measure
di: Liu, Shuainan, et al.
Pubblicazione: (2025)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
di: Kim, Hee-Seon, et al.
Pubblicazione: (2024)

Rethinking and Red-Teaming Protective Perturbation in Personalized Diffusion Models
di: Liu, Yixin, et al.
Pubblicazione: (2024)

Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence
di: Chen, Ruoxi, et al.
Pubblicazione: (2021)

Detecting AutoAttack Perturbations in the Frequency Domain
di: Lorenz, Peter, et al.
Pubblicazione: (2021)

Robustness of Vision Foundation Models to Common Perturbations
di: Liu, Hongbin, et al.
Pubblicazione: (2026)

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation
di: Yang, Hao, et al.
Pubblicazione: (2026)

Fooling the Image Dehazing Models by First Order Gradient
di: Gui, Jie, et al.
Pubblicazione: (2023)

FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution
di: Zhou, Qi, et al.
Pubblicazione: (2024)

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

SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts
di: Wu, Xiaodong, et al.
Pubblicazione: (2025)

Output Perturbation for Differentially Private Convex Optimization: Faster and More General
di: Lowy, Andrew, et al.
Pubblicazione: (2021)

Adversarial Universal Stickers: Universal Perturbation Attacks on Traffic Sign using Stickers
di: Etim, Anthony, et al.
Pubblicazione: (2025)

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

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

ProP: Efficient Backdoor Detection via Propagation Perturbation for Overparametrized Models
di: Ren, Tao, et al.
Pubblicazione: (2024)

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

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

Technical Report for ICML 2024 TiFA Workshop MLLM Attack Challenge: Suffix Injection and Projected Gradient Descent Can Easily Fool An MLLM
di: Guo, Yangyang, et al.
Pubblicazione: (2024)

Certified but Fooled! Breaking Certified Defences with Ghost Certificates
di: Vo, Quoc Viet, et al.
Pubblicazione: (2025)

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

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

User-wise Perturbations for User Identity Protection in EEG-Based BCIs
di: Chen, Xiaoqing, et al.
Pubblicazione: (2024)

Cross-Input Certified Training for Universal Perturbations
di: Xu, Changming, et al.
Pubblicazione: (2024)

GCON: Differentially Private Graph Convolutional Network via Objective Perturbation
di: Wei, Jianxin, et al.
Pubblicazione: (2024)

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
di: Meng, Jiayang, et al.
Pubblicazione: (2025)

DUAP: Dual-task Universal Adversarial Perturbations Against Voice Control Systems
di: Sun, Suyang, et al.
Pubblicazione: (2026)

Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation
di: Waghela, Hetvi, et al.
Pubblicazione: (2024)

RoMA: Robust Malware Attribution via Byte-level Adversarial Training with Global Perturbations and Adversarial Consistency Regularization
di: Sun, Yuxia, et al.
Pubblicazione: (2025)

Intermediate Outputs Are More Sensitive Than You Think
di: Huang, Tao, et al.
Pubblicazione: (2024)

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

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