Cover Image

Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Junxi, Dong, Junhao, Xie, Xiaohua
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability
by: Chen, Junxi, et al.
Published: (2024)

Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges
by: Dong, Junhao, et al.
Published: (2023)

MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
by: Liu, Yilian, et al.
Published: (2026)

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
by: Jin, Haibo, et al.
Published: (2021)

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

PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
by: Yuan, Lingzhi, et al.
Published: (2025)

Antelope: Potent and Concealed Jailbreak Attack Strategy
by: Zhao, Xin, et al.
Published: (2024)

Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning
by: Zhang, Chenyu, et al.
Published: (2025)

Text is All You Need for Vision-Language Model Jailbreaking
by: Chen, Yihang, et al.
Published: (2026)

An Experimental Study of Trojan Vulnerabilities in UAV Autonomous Landing
by: Ahmari, Reza, et al.
Published: (2025)

DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
by: Li, Boheng, et al.
Published: (2025)

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
by: Jiang, Zhengyuan, et al.
Published: (2025)

Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models
by: Liang, Shuang, et al.
Published: (2025)

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model
by: Zhang, Chenyu, et al.
Published: (2025)

PLA: Prompt Learning Attack against Text-to-Image Generative Models
by: Lyu, Xinqi, et al.
Published: (2025)

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

Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions
by: Nagaraja, Neha, et al.
Published: (2026)

Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications
by: Trad, Fouad, et al.
Published: (2024)

Multimodal Pragmatic Jailbreak on Text-to-image Models
by: Liu, Tong, et al.
Published: (2024)

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step
by: Wang, Wenxuan, et al.
Published: (2024)

Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
by: Maljkovic, Igor, et al.
Published: (2026)

Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
by: Zhu, Rui, et al.
Published: (2022)

Solving Trojan Detection Competitions with Linear Weight Classification
by: Huster, Todd, et al.
Published: (2024)

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks
by: Hao, Run, et al.
Published: (2025)

IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis
by: Zhang, Lingyun, et al.
Published: (2026)

Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification
by: Meng, Xiangtao, et al.
Published: (2025)

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security
by: Fang, Xiang, et al.
Published: (2026)

Adaptive Probe-based Steering for Robust LLM Jailbreaking
by: Chen, Junxi, et al.
Published: (2026)

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

SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
by: Zhang, Hongxiang, et al.
Published: (2024)

DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization
by: Dang, Pucheng, et al.
Published: (2024)

Dormant: Defending against Pose-driven Human Image Animation
by: Zhou, Jiachen, et al.
Published: (2024)

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

Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
by: Schaeffer, Rylan, et al.
Published: (2024)

Backdoor Attacks against Image-to-Image Networks
by: Jiang, Wenbo, et al.
Published: (2024)

SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability
by: Xu, Peiyang, et al.
Published: (2025)

Value-Aligned Prompt Moderation via Zero-Shot Agentic Rewriting for Safe Image Generation
by: Zhao, Xin, et al.
Published: (2025)

Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization
by: Chen, Rui, et al.
Published: (2025)

When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
by: Tian, Yuan, et al.
Published: (2026)

ICAS: Detecting Training Data from Autoregressive Image Generative Models
by: Yu, Hongyao, et al.
Published: (2025)