Imagen de Portada

The Illusion of Forgetting: Attack Unlearned Diffusion via Initial Latent Variable Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Manyi, Liu, Yufan, Jiang, Lai, Li, Bing, Li, Yuming, Hu, Weiming
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Computers and Society
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Dataset Distillation: Lossless Dataset Concentration via Diffusion-Assisted Distribution Alignment
por: Liu, Tongfei, et al.
Publicado: (2026)

Token Caching for Diffusion Transformer Acceleration
por: Lou, Jinming, et al.
Publicado: (2024)

Arbitrary Ratio Feature Compression via Next Token Prediction
por: Liu, Yufan, et al.
Publicado: (2026)

Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
por: Deng, Kaiyuan, et al.
Publicado: (2026)

Exploring the Adversarial Robustness of Face Forgery Detection with Decision-based Black-box Attacks
por: Chen, Zhaoyu, et al.
Publicado: (2023)

FreeInit: Bridging Initialization Gap in Video Diffusion Models
por: Wu, Tianxing, et al.
Publicado: (2023)

Visual-Instructed Degradation Diffusion for All-in-One Image Restoration
por: Luo, Wenyang, et al.
Publicado: (2025)

Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective
por: Han, Xiaoxuan, et al.
Publicado: (2024)

Saliency Guided Optimization of Diffusion Latents
por: Wang, Xiwen, et al.
Publicado: (2024)

InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization
por: Guo, Xiefan, et al.
Publicado: (2024)

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

The Evolving Nature of Latent Spaces: From GANs to Diffusion
por: Schaerf, Ludovica
Publicado: (2025)

Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model
por: Wang, Zhaonan, et al.
Publicado: (2025)

QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization
por: Xu, Yuhao, et al.
Publicado: (2026)

Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model
por: Huang, Lin-Chun, et al.
Publicado: (2025)

An Effective Image Copy-Move Forgery Detection Using Entropy Information
por: Jiang, Li, et al.
Publicado: (2023)

CLIP-based Point Cloud Classification via Point Cloud to Image Translation
por: Ghose, Shuvozit, et al.
Publicado: (2024)

Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing
por: Yang, Zizheng, et al.
Publicado: (2025)

Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval
por: Liu, Haowei, et al.
Publicado: (2024)

Decoding Tourist Perception in Historic Urban Quarters with Multimodal Social Media Data: An AI-Based Framework and Evidence from Shanghai
por: Tan, Kaizhen, et al.
Publicado: (2025)

Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering Human Perceptual Variability on Facial Expressions
por: Deng, Haotian, et al.
Publicado: (2025)

Fair Text-to-Image Diffusion via Fair Mapping
por: Li, Jia, et al.
Publicado: (2023)

AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing
por: Wang, Zhaonan, et al.
Publicado: (2025)

Training-Free Multimodal Deepfake Detection via Graph Reasoning
por: Liu, Yuxin, et al.
Publicado: (2025)

FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editing
por: Ren, Yufan, et al.
Publicado: (2025)

Designing to Forget: Deep Semi-parametric Models for Unlearning
por: Zheng, Amber Yijia, et al.
Publicado: (2026)

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation
por: Li, Zhiheng, et al.
Publicado: (2026)

Prompting Forgetting: Unlearning in GANs via Textual Guidance
por: Nagasubramaniam, Piyush, et al.
Publicado: (2025)

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
por: Deng, Kaiyuan, et al.
Publicado: (2026)

EmoAssist: Emotional Assistant for Visual Impairment Community
por: Qi, Xingyu, et al.
Publicado: (2025)

The Dual Power of Interpretable Token Embeddings: Jailbreaking Attacks and Defenses for Diffusion Model Unlearning
por: Chen, Siyi, et al.
Publicado: (2025)

StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions
por: Ke, Bo-Hsu, et al.
Publicado: (2025)

ViMU: Benchmarking Video Metaphorical Understanding
por: Li, Qi, et al.
Publicado: (2026)

TrajSceneLLM: A Multimodal Perspective on Semantic GPS Trajectory Analysis
por: Ji, Chunhou, et al.
Publicado: (2025)

TriAlignXA: An Explainable Trilemma Alignment Framework for Trustworthy Agri-product Grading
por: Xie, Jianfei, et al.
Publicado: (2025)

FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts
por: Bai, Tongyuan, et al.
Publicado: (2025)

Controlling the Latent Diffusion Model for Generative Image Shadow Removal via Residual Generation
por: Li, Xinjie, et al.
Publicado: (2024)

Hierarchical Semantic Compression for Consistent Image Semantic Restoration
por: Li, Shengxi, et al.
Publicado: (2025)

EgoPrivacy: What Your First-Person Camera Says About You?
por: Li, Yijiang, et al.
Publicado: (2025)

SoLA-Vision: Fine-grained Layer-wise Linear Softmax Hybrid Attention
por: Li, Ruibang, et al.
Publicado: (2026)