Imagen de Portada

Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Koma, Arian Komaei, Kasaei, Seyed Amir, Sadeghzadeh, AmirMahdi, Rohban, Mohammad Hossein
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
por: Koma, Arian Komaei, et al.
Publicado: (2026)

Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation
por: Kasaei, Seyed Amir, et al.
Publicado: (2025)

Evaluating the Evaluators: Metrics for Compositional Text-to-Image Generation
por: Kasaei, Seyed Amir, et al.
Publicado: (2025)

Hidden Meanings in Plain Sight: RebusBench for Evaluating Cognitive Visual Reasoning
por: Kasaei, Seyed Amir, et al.
Publicado: (2026)

CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration
por: Kasaei, Seyed Amir, et al.
Publicado: (2025)

All Centers Are at most a Few Tokens Apart: Knowledge Distillation with Domain Invariant Prompt Tuning
por: Ezzati, Amir Mohammad, et al.
Publicado: (2025)

No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
por: Sameti, Mohammad Hossein, et al.
Publicado: (2025)

Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models
por: Marioriyad, Arash, et al.
Publicado: (2024)

Enriching Knowledge Distillation with Cross-Modal Teacher Fusion
por: Mansourian, Amir M., et al.
Publicado: (2025)

Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning
por: Fuchi, Masane, et al.
Publicado: (2024)

Deep Spectral Improvement for Unsupervised Image Instance Segmentation
por: Arefi, Farnoosh, et al.
Publicado: (2024)

KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation
por: Davoodi, Farbod, et al.
Publicado: (2026)

Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions
por: Razlighi, AmirHossein Naghi, et al.
Publicado: (2025)

Attention Overlap Is Responsible for The Entity Missing Problem in Text-to-image Diffusion Models!
por: Marioriyad, Arash, et al.
Publicado: (2024)

PromptLA: Towards Integrity Verification of Black-box Text-to-Image Diffusion Models
por: Zhang, Zhuomeng, et al.
Publicado: (2024)

What Are We Really Measuring? Rethinking Dataset Bias in Web-Scale Natural Image Collections via Unsupervised Semantic Clustering
por: Saleknia, Amir Hossein, et al.
Publicado: (2026)

Erase at the Core: Representation Unlearning for Machine Unlearning
por: Lee, Jaewon, et al.
Publicado: (2026)

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models
por: Rezaei, Parham, et al.
Publicado: (2025)

Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal Consistency
por: Arefi, Farnoosh, et al.
Publicado: (2024)

Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
por: He, Yutong, et al.
Publicado: (2024)

T2I-FineEval: Fine-Grained Compositional Metric for Text-to-Image Evaluation
por: Hosseini, Seyed Mohammad Hadi, et al.
Publicado: (2025)

Extracting Overlapping Microservices from Monolithic Code via Deep Semantic Embeddings and Graph Neural Network-Based Soft Clustering
por: Ziabakhsh, Morteza, et al.
Publicado: (2025)

Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
por: Mirzaei, Hossein, et al.
Publicado: (2025)

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
por: Aladawi, Aljalila, et al.
Publicado: (2026)

Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models
por: Shin, Jiwoo, et al.
Publicado: (2025)

Deep Nonlinear Hyperspectral Unmixing Using Multi-task Learning
por: Mehrdad, Saeid, et al.
Publicado: (2024)

Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models
por: Abbasi, Reza, et al.
Publicado: (2024)

Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation
por: Izadi, Amir Mohammad, et al.
Publicado: (2025)

Probing Multimodal Fusion in the Brain: The Dominance of Audiovisual Streams in Naturalistic Encoding
por: Abdollahi, Hamid, et al.
Publicado: (2025)

Attention-guided Feature Distillation for Semantic Segmentation
por: Mansourian, Amir M., et al.
Publicado: (2024)

Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers
por: Huang, Chi-Pin, et al.
Publicado: (2023)

Novel Pipeline for Diagnosing Acute Lymphoblastic Leukemia Sensitive to Related Biomarkers
por: Farsangi, Amirhossein Askari, et al.
Publicado: (2023)

Black-box Adversarial Attacks Against Image Quality Assessment Models
por: Ran, Yu, et al.
Publicado: (2024)

Snuffy: Efficient Whole Slide Image Classifier
por: Jafarinia, Hossein, et al.
Publicado: (2024)

Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models
por: Sridhar, Deepak, et al.
Publicado: (2024)

Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
por: Seo, Hoigi, et al.
Publicado: (2026)

Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
por: Zohrabi, Reihaneh, et al.
Publicado: (2025)

Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
por: Abbasi, Reza, et al.
Publicado: (2024)

TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models
por: Xiang, Qianlong, et al.
Publicado: (2026)

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
por: Tian, Zhihua, et al.
Publicado: (2025)