Cover Image

REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zou, Yong, Li, Haoran, Li, Fanxiao, Wei, Shenyang, Dong, Yunyun, Tang, Li, Zhou, Wei, Liu, Renyang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
by: Liu, Renyang, et al.
Published: (2025)

Rethinking Machine Unlearning in Image Generation Models
by: Liu, Renyang, et al.
Published: (2025)

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
by: Li, Fanxiao, et al.
Published: (2026)

When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
by: Zhao, Shiqian, et al.
Published: (2025)

MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
by: Wang, Yanting, et al.
Published: (2024)

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
by: Lin, Weilin, et al.
Published: (2024)

CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models
by: Liu, Renyang, et al.
Published: (2026)

Universal Anti-forensics Attack against Image Forgery Detection via Multi-modal Guidance
by: Li, Haipeng, et al.
Published: (2026)

Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks
by: Diao, Yunfeng, et al.
Published: (2024)

SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models
by: Liu, Renyang, et al.
Published: (2026)

UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
by: Xue, Lulu, et al.
Published: (2026)

Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
by: Bertran, Martin, et al.
Published: (2024)

JNI Global References Are Still Vulnerable: Attacks and Defenses
by: He, Yi, et al.
Published: (2024)

On the Multi-modal Vulnerability of Diffusion Models
by: Yang, Dingcheng, et al.
Published: (2024)

Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
by: Xiong, Yuan, et al.
Published: (2025)

Label Inference Attacks against Federated Unlearning
by: Wang, Wei, et al.
Published: (2025)

Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
by: Li, Jun, et al.
Published: (2026)

FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks
by: Chen, Jian, et al.
Published: (2025)

AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization
by: Li, Jiyao, et al.
Published: (2024)

Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning
by: Hu, Hongsheng, et al.
Published: (2024)

Multi-Target Federated Backdoor Attack Based on Feature Aggregation
by: Hao, Lingguag, et al.
Published: (2025)

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
by: Qi, Senmao, et al.
Published: (2025)

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

When Backdoors Go Beyond Triggers: Semantic Drift in Diffusion Models Under Encoder Attacks
by: Chen, Shenyang, et al.
Published: (2026)

Stego Battlefield: Evaluating Image Steganography Attacks and Steganalysis Defenses
by: Sun, Zhen, et al.
Published: (2026)

The Orthogonal Vulnerabilities of Generative AI Watermarks: A Comparative Empirical Benchmark of Spatial and Latent Provenance
by: Yu, Jesse, et al.
Published: (2026)

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation
by: Zhang, Jiankun, et al.
Published: (2025)

A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
by: Li, Ziqiang, et al.
Published: (2023)

ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models
by: Yook, Hyun Jun, et al.
Published: (2025)

BlockFUL: Enabling Unlearning in Blockchained Federated Learning
by: Liu, Xiao, et al.
Published: (2024)

Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach
by: Huang, Linhao, et al.
Published: (2025)

Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning
by: Ye, Dayong, et al.
Published: (2025)

Membership Inference Attack Against Masked Image Modeling
by: Li, Zheng, et al.
Published: (2024)

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
by: He, Yuhao, et al.
Published: (2024)

Stealthy Multi-Task Adversarial Attacks
by: Guo, Jiacheng, et al.
Published: (2024)

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
by: Chen, Yulin, et al.
Published: (2025)

Systematic Categorization, Construction and Evaluation of New Attacks against Multi-modal Mobile GUI Agents
by: Yang, Yulong, et al.
Published: (2024)

An Investigation of Large Language Models and Their Vulnerabilities in Spam Detection
by: Tang, Qiyao, et al.
Published: (2025)

Detecting Complex Multi-step Attacks with Explainable Graph Neural Network
by: Liu, Wei, et al.
Published: (2024)

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
by: Gao, Hongcheng, et al.
Published: (2024)