Cover Image

When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Shiqian, Liu, Jiayang, Li, Yiming, Hu, Runyi, Jia, Xiaojun, Fan, Wenshu, Bao, Xiao, Li, Xinfeng, Zhang, Jie, Dong, Wei, Zhang, Tianwei, Tuan, Luu Anh
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers
by: Nguyen, Viet-Anh, et al.
Published: (2025)

SAME: Sample Reconstruction against Model Extraction Attacks
by: Xie, Yi, et al.
Published: (2023)

Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models
by: Zhao, Shiqian, et al.
Published: (2025)

Robust-Wide: Robust Watermarking against Instruction-driven Image Editing
by: Hu, Runyi, et al.
Published: (2024)

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
by: Zhao, Shuai, et al.
Published: (2023)

Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
by: Zhao, Shuai, et al.
Published: (2024)

T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
by: Liu, Jiayang, et al.
Published: (2025)

Mask Image Watermarking
by: Hu, Runyi, et al.
Published: (2025)

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
by: Teng, Ma, et al.
Published: (2024)

Perception-guided Jailbreak against Text-to-Image Models
by: Huang, Yihao, et al.
Published: (2024)

TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking
by: Meng, Jiale, et al.
Published: (2026)

Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
by: Hu, Hanjiang, et al.
Published: (2025)

SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution
by: Hu, Runyi, et al.
Published: (2024)

VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
by: Hu, Runyi, et al.
Published: (2025)

AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
by: Chen, Guangke, et al.
Published: (2025)

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
by: Jia, Xiaojun, et al.
Published: (2025)

SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA
by: Zhang, Siyue, et al.
Published: (2024)

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
by: Chen, Kejia, et al.
Published: (2026)

BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models
by: Yan, Xiaobei, et al.
Published: (2025)

On the Vulnerability of Text Sanitization
by: Tong, Meng, et al.
Published: (2024)

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
by: Ma, Jiachen, et al.
Published: (2024)

Enhancing Jailbreak Attacks with Diversity Guidance
by: Zhang, Xu, et al.
Published: (2024)

Stealthy Targeted Backdoor Attacks against Image Captioning
by: Fan, Wenshu, et al.
Published: (2024)

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
by: Hou, Jiacheng, et al.
Published: (2026)

Inference-time Alignment via Sparse Junction Steering
by: Hu, Runyi, et al.
Published: (2026)

Backdoor Attacks against Hybrid Classical-Quantum Neural Networks
by: Guo, Ji, et al.
Published: (2024)

Useful Memories Become Faulty When Continuously Updated by LLMs
by: Zhang, Dylan, et al.
Published: (2026)

Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography
by: Li, Songze, et al.
Published: (2025)

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
by: Weng, Zixuan, et al.
Published: (2025)

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
by: Zhao, Shuai, et al.
Published: (2025)

POEX: Towards Policy Executable Jailbreak Attacks Against the LLM-based Robots
by: Lu, Xuancun, et al.
Published: (2024)

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

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

Untargeted Jailbreak Attack
by: Huang, Xinzhe, et al.
Published: (2025)

PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage
by: Zhang, Wenyi, et al.
Published: (2025)

Discrete Diffusion Language Model for Efficient Text Summarization
by: Dat, Do Huu, et al.
Published: (2024)

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
by: Zhao, Shuai, et al.
Published: (2024)

Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution
by: Zhang, Yechao, et al.
Published: (2026)

Enriching and Controlling Global Semantics for Text Summarization
by: Nguyen, Thong, et al.
Published: (2021)

Metaphor-based Jailbreak Attacks on Text-to-Image Models
by: Zhang, Chenyu, et al.
Published: (2025)