Copertina

Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Le, Ying, Zonghao, Zhang, Tianyuan, Liang, Siyuan, Hu, Shengshan, Zhang, Mingchuan, Liu, Aishan, Liu, Xianglong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
di: Ying, Zonghao, et al.
Pubblicazione: (2024)

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation
di: Jing, Zonglei, et al.
Pubblicazione: (2025)

Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving
di: Zhang, Tianyuan, et al.
Pubblicazione: (2025)

Towards Robust Physical-world Backdoor Attacks on Lane Detection
di: Zhang, Xinwei, et al.
Pubblicazione: (2024)

CogMorph: Cognitive Morphing Attacks for Text-to-Image Models
di: Jing, Zonglei, et al.
Pubblicazione: (2025)

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
di: Zhang, Tianyuan, et al.
Pubblicazione: (2024)

Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles
di: Liu, Jiangfan, et al.
Pubblicazione: (2025)

Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks
di: Ying, Zonghao, et al.
Pubblicazione: (2024)

LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions
di: Zhang, Tianyuan, et al.
Pubblicazione: (2024)

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
di: Ying, Zonghao, et al.
Pubblicazione: (2025)

Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving
di: Zhang, Tianyuan, et al.
Pubblicazione: (2024)

SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge
di: Ying, Zonghao, et al.
Pubblicazione: (2025)

Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving
di: Wang, Lu, et al.
Pubblicazione: (2025)

RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
di: Wang, Le, et al.
Pubblicazione: (2025)

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

RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation
di: Liu, Enguang, et al.
Pubblicazione: (2025)

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

Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models
di: Cheng, Hao, et al.
Pubblicazione: (2025)

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
di: Liang, Jiawei, et al.
Pubblicazione: (2024)

ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt
di: Zeng, Fanhu, et al.
Pubblicazione: (2024)

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

GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing
di: Xiao, Yisong, et al.
Pubblicazione: (2024)

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
di: Liang, Jiawei, et al.
Pubblicazione: (2024)

Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation
di: Liang, Jiawei, et al.
Pubblicazione: (2022)

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation
di: Yang, Hao, et al.
Pubblicazione: (2026)

Rad-VLSM: A Cross-Modal Framework with Semantics-Assisted Prompting for Medical Segmentation and Diagnosis
di: Zhang, Fengyi, et al.
Pubblicazione: (2026)

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
di: Wang, Xuan, et al.
Pubblicazione: (2025)

Multimodal Emotion Recognition with Vision-language Prompting and Modality Dropout
di: QI, Anbin, et al.
Pubblicazione: (2024)

CoDefend: Cross-Modal Collaborative Defense via Diffusion Purification and Prompt Optimization
di: Zhu, Fengling, et al.
Pubblicazione: (2025)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
di: Ying, Zonghao, et al.
Pubblicazione: (2026)

Attribution-Guided Multimodal Deepfake Detection via Cross-Modal Forensic Fingerprints
di: Ahmad, Wasim, et al.
Pubblicazione: (2026)

Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
di: Hu, Tao, et al.
Pubblicazione: (2026)

REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detection
di: Zhou, Jun, et al.
Pubblicazione: (2026)

Combating Visual Neglect and Semantic Drift in Large Multimodal Models for Enhanced Cross-Modal Retrieval
di: Zhang, Guosheng, et al.
Pubblicazione: (2026)

Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization
di: Zhang, Yanghai, et al.
Pubblicazione: (2024)

Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers
di: Liu, Yuhe, et al.
Pubblicazione: (2026)

Progressive Prompt-Guided Cross-Modal Reasoning for Referring Image Segmentation
di: Li, Jiachen, et al.
Pubblicazione: (2026)

Physical Prompt Injection Attacks on Large Vision-Language Models
di: Ling, Chen, et al.
Pubblicazione: (2026)

Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
di: Hu, Jin, et al.
Pubblicazione: (2025)

Open-set Cross Modal Generalization via Multimodal Unified Representation
di: Huang, Hai, et al.
Pubblicazione: (2025)