Cover Image

The Dual Power of Interpretable Token Embeddings: Jailbreaking Attacks and Defenses for Diffusion Model Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Siyi, Zhang, Yimeng, Liu, Sijia, Qu, Qing
Format:	Preprint
Published:	2025
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

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
by: Zhang, Yimeng, et al.
Published: (2024)

To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
by: Zhang, Yimeng, et al.
Published: (2023)

UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
by: Zhang, Yihua, et al.
Published: (2024)

The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
by: Guo, Yangyang, et al.
Published: (2024)

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
by: Liu, Xuannan, et al.
Published: (2024)

HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
by: Gao, Sensen, et al.
Published: (2024)

Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
by: Liang, Siyuan, et al.
Published: (2024)

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
by: Zhao, Yunhan, et al.
Published: (2025)

Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering
by: Wang, Peng, et al.
Published: (2024)

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

Exploring Low-Dimensional Subspaces in Diffusion Models for Controllable Image Editing
by: Chen, Siyi, et al.
Published: (2024)

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

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
by: Li, Xiao, et al.
Published: (2025)

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
by: Patil, Vaidehi, et al.
Published: (2025)

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
by: Chen, Beitao, et al.
Published: (2025)

A Low-Rank Defense Method for Adversarial Attack on Diffusion Models
by: Zhu, Jiaxuan, et al.
Published: (2026)

Backdoor Defense in Diffusion Models via Spatial Attention Unlearning
by: Jha, Abha, et al.
Published: (2025)

Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models
by: Zhu, Xingyu, et al.
Published: (2026)

Language-Guided Diffusion Model for Visual Grounding
by: Chen, Sijia, et al.
Published: (2023)

Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splitting
by: Tran, Bao Q., et al.
Published: (2024)

Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models
by: Ying, Zonghao, et al.
Published: (2026)

ID-Patch: Robust ID Association for Group Photo Personalization
by: Zhang, Yimeng, et al.
Published: (2024)

Understanding Generalization in Diffusion Distillation via Probability Flow Distance
by: Zhang, Huijie, et al.
Published: (2025)

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure
by: Xue, Lulu, et al.
Published: (2025)

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

A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models
by: Truong, Vu Tuan, et al.
Published: (2025)

Debiased Dual-Invariant Defense for Adversarially Robust Person Re-Identification
by: Zhou, Yuhang, et al.
Published: (2025)

Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models
by: Li, Yize, et al.
Published: (2024)

OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
by: Jia, Xiaojun, et al.
Published: (2025)

Unfolding Videos Dynamics via Taylor Expansion
by: Chen, Siyi, et al.
Published: (2024)

Why Instruction-Based Unlearning Fails in Diffusion Models?
by: Zhang, Zeliang, et al.
Published: (2026)

LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models
by: Zhang, Dingkun, et al.
Published: (2024)

Attack for Defense: Adversarial Agents for Point Prompt Optimization Empowering Segment Anything Model
by: Liu, Xueyu, et al.
Published: (2025)

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

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings
by: Xu, Jingqi, et al.
Published: (2025)

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
by: Jiang, Lei, et al.
Published: (2025)

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
by: Liang, Siyuan, et al.
Published: (2023)

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

Proxy-Embedding as an Adversarial Teacher: An Embedding-Guided Bidirectional Attack for Referring Expression Segmentation Models
by: Chen, Xingbai, et al.
Published: (2025)

Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
by: Ge, Yuying, et al.
Published: (2024)