Copertina

Latent Diffusion Unlearning: Protecting Against Unauthorized Personalization Through Trajectory Shifted Perturbations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Devulapally, Naresh Kumar, Agarwal, Shruti, Gokhale, Tejas, Lokhande, Vishnu Suresh
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Your Text Encoder Can Be An Object-Level Watermarking Controller
di: Devulapally, Naresh Kumar, et al.
Pubblicazione: (2025)

Score-Control for Hallucination Reduction in Diffusion Models
di: Bhosale, Mahesh, et al.
Pubblicazione: (2026)

Forget Less by Learning from Parents Through Hierarchical Relationships
di: Kaushik, Arjun Ramesh, et al.
Pubblicazione: (2026)

Forget Less by Learning Together through Concept Consolidation
di: Kaushik, Arjun Ramesh, et al.
Pubblicazione: (2026)

Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder
di: Wu, Chao, et al.
Pubblicazione: (2025)

Personalized Privacy Protection Mask Against Unauthorized Facial Recognition
di: Chow, Ka-Ho, et al.
Pubblicazione: (2024)

Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation
di: Peng, Sen, et al.
Pubblicazione: (2024)

Pooling Image Datasets With Multiple Covariate Shift and Imbalance
di: Chytas, Sotirios Panagiotis, et al.
Pubblicazione: (2024)

Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling
di: Saha, Sourajit, et al.
Pubblicazione: (2024)

Craft: Cross-modal Aligned Features Improve Robustness of Prompt Tuning
di: Sun, Jingchen, et al.
Pubblicazione: (2024)

ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation
di: Roy, Ayush, et al.
Pubblicazione: (2026)

Is Exchangeability better than I.I.D to handle Data Distribution Shifts while Pooling Data for Data-scarce Medical image segmentation?
di: Roy, Ayush, et al.
Pubblicazione: (2025)

ParallelEdits: Efficient Multi-object Image Editing
di: Huang, Mingzhen, et al.
Pubblicazione: (2024)

Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation
di: Zhao, Zhengyue, et al.
Pubblicazione: (2023)

Targeted Attack Improves Protection against Unauthorized Diffusion Customization
di: Zheng, Boyang, et al.
Pubblicazione: (2023)

Side Effects of Erasing Concepts from Diffusion Models
di: Saha, Shaswati, et al.
Pubblicazione: (2025)

Grounding Stylistic Domain Generalization with Quantitative Domain Shift Measures and Synthetic Scene Images
di: Luo, Yiran, et al.
Pubblicazione: (2024)

AM^2-EmoJE: Adaptive Missing-Modality Emotion Recognition in Conversation via Joint Embedding Learning
di: Devulapally, Naresh Kumar, et al.
Pubblicazione: (2024)

Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models
di: Ahn, Namhyuk, et al.
Pubblicazione: (2024)

CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
di: Peng, Sen, et al.
Pubblicazione: (2025)

ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
di: Patel, Maitreya, et al.
Pubblicazione: (2023)

Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
di: Zhao, Zhengyue, et al.
Pubblicazione: (2023)

EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models
di: Chen, Ruoxi, et al.
Pubblicazione: (2023)

Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
di: Li, Boheng, et al.
Pubblicazione: (2024)

On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
di: Chatterjee, Agneet, et al.
Pubblicazione: (2024)

Defense against Unauthorized Distillation in Image Restoration via Feature Space Perturbation
di: Hu, Han, et al.
Pubblicazione: (2025)

Anti-Tamper Protection for Unauthorized Individual Image Generation
di: Li, Zelin, et al.
Pubblicazione: (2025)

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
di: Cui, Yingqian, et al.
Pubblicazione: (2023)

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

ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation
di: Luo, Ziyuan, et al.
Pubblicazione: (2025)

REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models
di: Chatterjee, Agneet, et al.
Pubblicazione: (2024)

VideoGuard: Protecting Video Content from Unauthorized Editing
di: Cao, Junjie, et al.
Pubblicazione: (2025)

The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches
di: Kumar, Vishesh, et al.
Pubblicazione: (2026)

CryptoFace: End-to-End Encrypted Face Recognition
di: Ao, Wei, et al.
Pubblicazione: (2025)

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
di: Zhou, Yifan, et al.
Pubblicazione: (2025)

MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use
di: Mohammadshirazi, Ahmad, et al.
Pubblicazione: (2025)

ProMark: Proactive Diffusion Watermarking for Causal Attribution
di: Asnani, Vishal, et al.
Pubblicazione: (2024)

Defending Unauthorized Model Merging via Dual-Stage Weight Protection
di: Chen, Wei-Jia, et al.
Pubblicazione: (2025)

Language-Guided Trajectory Traversal in Disentangled Stable Diffusion Latent Space for Factorized Medical Image Generation
di: TehraniNasab, Zahra, et al.
Pubblicazione: (2025)

Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models
di: Li, Qifan, et al.
Pubblicazione: (2026)