Imagen de Portada

Test-Time Backdoor Attacks on Multimodal Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lu, Dong, Pang, Tianyu, Du, Chao, Liu, Qian, Yang, Xianjun, Lin, Min
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Cryptography and Security Computer Vision and Pattern Recognition Machine Learning Multimedia
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Benchmarking Large Multimodal Models against Common Corruptions
por: Zhang, Jiawei, et al.
Publicado: (2024)

VideoSTF: Stress-Testing Output Repetition in Video Large Language Models
por: Cao, Yuxin, et al.
Publicado: (2026)

SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings
por: Lu, Weikai, et al.
Publicado: (2025)

BadCM: Invisible Backdoor Attack Against Cross-Modal Learning
por: Zhang, Zheng, et al.
Publicado: (2024)

VVRec: Reconstruction Attacks on DL-based Volumetric Video Upstreaming via Latent Diffusion Model with Gamma Distribution
por: Lu, Rui, et al.
Publicado: (2025)

From Attack to Protection: Leveraging Watermarking Attack Network for Advanced Add-on Watermarking
por: Nam, Seung-Hun, et al.
Publicado: (2020)

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

Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
por: Fu, Jiyuan, et al.
Publicado: (2024)

Natural Language Induced Adversarial Images
por: Zhu, Xiaopei, et al.
Publicado: (2024)

Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
por: Huang, Xijie, et al.
Publicado: (2024)

A Multi-task Adversarial Attack Against Face Authentication
por: Wang, Hanrui, et al.
Publicado: (2024)

Universally Unfiltered and Unseen:Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards
por: Yan, Song, et al.
Publicado: (2025)

DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection
por: Zhao, Kangran, et al.
Publicado: (2025)

Denial-of-Service Poisoning Attacks against Large Language Models
por: Gao, Kuofeng, et al.
Publicado: (2024)

CoreMark: Toward Robust and Universal Text Watermarking Technique
por: Meng, Jiale, et al.
Publicado: (2025)

Provably Secure Robust Image Steganography via Cross-Modal Error Correction
por: Qi, Yuang, et al.
Publicado: (2024)

Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs
por: Li, Jinmin, et al.
Publicado: (2024)

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

Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations
por: Mareen, Hannes, et al.
Publicado: (2024)

Wallcamera: Reinventing the Wheel?
por: Bourquard, Aurélien, et al.
Publicado: (2024)

ByteNet: Rethinking Multimedia File Fragment Classification through Visual Perspectives
por: Liu, Wenyang, et al.
Publicado: (2024)

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
por: Gu, Xiangming, et al.
Publicado: (2024)

VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models
por: Li, Xiang, et al.
Publicado: (2023)

Test-Time Attention Purification for Backdoored Large Vision Language Models
por: Zhang, Zhifang, et al.
Publicado: (2026)

IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding
por: Li, Junxian, et al.
Publicado: (2025)

Jailbreaking Attack against Multimodal Large Language Model
por: Niu, Zhenxing, et al.
Publicado: (2024)

Task-Agnostic Detector for Insertion-Based Backdoor Attacks
por: Lyu, Weimin, et al.
Publicado: (2024)

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

DKiS: Decay weight invertible image steganography with private key
por: Yang, Hang, et al.
Publicado: (2023)

Clean-image Backdoor Attacks
por: Rong, Dazhong, et al.
Publicado: (2024)

Inevitable Encounters: Backdoor Attacks Involving Lossy Compression
por: Li, Qian, et al.
Publicado: (2026)

TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark
por: Mareen, Hannes, et al.
Publicado: (2026)

TGIF: Text-Guided Inpainting Forgery Dataset
por: Mareen, Hannes, et al.
Publicado: (2024)

Is It Really You? Exploring Biometric Verification Scenarios in Photorealistic Talking-Head Avatar Videos
por: Pedrouzo-Rodriguez, Laura, et al.
Publicado: (2025)

SWIFT: Semantic Watermarking for Image Forgery Thwarting
por: Evennou, Gautier, et al.
Publicado: (2024)

Backdoor Attack with Mode Mixture Latent Modification
por: Zhang, Hongwei, et al.
Publicado: (2024)

Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending
por: Pan, Yongyang, et al.
Publicado: (2024)

BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators
por: Tian, Yu, et al.
Publicado: (2024)

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
por: Yin, Ziyi, et al.
Publicado: (2023)

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
por: Wei, Shaokui, et al.
Publicado: (2024)