Cover Image

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Aladawi, Aljalila, Alam, Mohammed Talha, Karray, Fakhri
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FLARE up your data: Diffusion-based Augmentation Method in Astronomical Imaging
by: Alam, Mohammed Talha, et al.
Published: (2024)

AstroSpy: On detecting Fake Images in Astronomy via Joint Image-Spectral Representations
by: Alam, Mohammed Talha, et al.
Published: (2024)

ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions
by: AlHindaassi, Fatmah, et al.
Published: (2025)

CosmoCLIP: Generalizing Large Vision-Language Models for Astronomical Imaging
by: Imam, Raza, et al.
Published: (2024)

FaceAnonyMixer: Cancelable Faces via Identity Consistent Latent Space Mixing
by: Alam, Mohammed Talha, et al.
Published: (2025)

AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection
by: Jiang, Yichen, et al.
Published: (2025)

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
by: Li, Qing, et al.
Published: (2025)

SPQR: A Standardized Benchmark for Modern Safety Alignment Methods in Text-to-Image Diffusion Models
by: Alam, Mohammed Talha, et al.
Published: (2025)

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
by: Wang, Zhongqi, et al.
Published: (2024)

Defending Against Frequency-Based Attacks with Diffusion Models
by: Amerehi, Fatemeh, et al.
Published: (2025)

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks
by: Chew, Oscar, et al.
Published: (2024)

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

Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models
by: Zhang, Ci, et al.
Published: (2026)

Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation
by: Jiang, Shiyi, et al.
Published: (2025)

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
by: Wu, Yongliang, et al.
Published: (2024)

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

Unlearning Concepts from Text-to-Video Diffusion Models
by: Liu, Shiqi, et al.
Published: (2024)

TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
by: Zou, Quanchen, et al.
Published: (2026)

SecureGaze: Defending Gaze Estimation Against Backdoor Attacks
by: Du, Lingyu, et al.
Published: (2025)

Vision Language Models for Dynamic Human Activity Recognition in Healthcare Settings
by: Abid, Abderrazek, et al.
Published: (2025)

Time Traveling to Defend Against Adversarial Example Attacks in Image Classification
by: Etim, Anthony, et al.
Published: (2024)

Blending Concepts with Text-to-Image Diffusion Models
by: Olearo, Lorenzo, et al.
Published: (2025)

Unified Prompt Attack Against Text-to-Image Generation Models
by: Peng, Duo, et al.
Published: (2025)

Concept Unlearning by Modeling Key Steps of Diffusion Process
by: Zhang, Chaoshuo, et al.
Published: (2025)

Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models
by: Koma, Arian Komaei, et al.
Published: (2026)

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection
by: Strack, Lukas, et al.
Published: (2023)

Fair Text to Medical Image Diffusion Model with Subgroup Distribution Aligned Tuning
by: Han, Xu, et al.
Published: (2024)

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

Visual Concept-driven Image Generation with Text-to-Image Diffusion Model
by: Rahman, Tanzila, et al.
Published: (2024)

Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
by: Moon, Saemi, et al.
Published: (2026)

GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models
by: Han, Ning, et al.
Published: (2025)

NL-MambaXCT: Self-Supervised Nested-Learning Mamba for Nomex Honeycomb X-ray CT Defect Classification
by: Aldoboni, Ghaleb, et al.
Published: (2026)

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
by: Gong, Chao, et al.
Published: (2024)

A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models
by: Ma, Rui, et al.
Published: (2024)

CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
by: Biswas, Shristi Das, et al.
Published: (2025)

Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning
by: Moon, Saemi, et al.
Published: (2024)

REMONI: An Autonomous System Integrating Wearables and Multimodal Large Language Models for Enhanced Remote Health Monitoring
by: Ho, Thanh Cong, et al.
Published: (2025)

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

Quran-MD: A Fine-Grained Multilingual Multimodal Dataset of the Quran
by: Salman, Muhammad Umar, et al.
Published: (2026)

Uncertainty-Aware SAR ATR: Defending Against Adversarial Attacks via Bayesian Neural Networks
by: Ye, Tian, et al.
Published: (2024)