Copertina

Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xia, Chengwei, Ma, Fan, Quan, Ruijie, Xu, Yunqiu, Zhan, Kun, Yang, Yi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adversarial-Guided Diffusion for Multimodal LLM Attacks
di: Xia, Chengwei, et al.
Pubblicazione: (2025)

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion
di: Miao, Honglei, et al.
Pubblicazione: (2024)

MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs
di: Xu, Yunqiu, et al.
Pubblicazione: (2024)

BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities
di: Tian, Zhibo, et al.
Pubblicazione: (2025)

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
di: Chen, Shuhang, et al.
Pubblicazione: (2025)

Hierarchical Consensus Network for Multiview Feature Learning
di: Xia, Chengwei, et al.
Pubblicazione: (2025)

InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification
di: Han, Qi, et al.
Pubblicazione: (2024)

Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity
di: Quan, Ruijie, et al.
Pubblicazione: (2024)

CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
di: Zhao, Shuai, et al.
Pubblicazione: (2023)

Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction
di: Zhang, Xu, et al.
Pubblicazione: (2025)

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
di: Ouyang, Kun, et al.
Pubblicazione: (2025)

UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
di: Jiang, Hong, et al.
Pubblicazione: (2026)

Insert Anything: Image Insertion via In-Context Editing in DiT
di: Song, Wensong, et al.
Pubblicazione: (2025)

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation
di: Li, Zhiheng, et al.
Pubblicazione: (2026)

UAVBench and UAVIT-1M: Benchmarking and Enhancing MLLMs for Low-Altitude UAV Vision-Language Understanding
di: Zhan, Yang, et al.
Pubblicazione: (2026)

Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment
di: Wang, Haobo, et al.
Pubblicazione: (2026)

IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images with Generative Visual Prompting
di: Zhang, Tao, et al.
Pubblicazione: (2025)

AudioScenic: Audio-Driven Video Scene Editing
di: Shen, Kaixin, et al.
Pubblicazione: (2024)

Reinforcing Consistency in Video MLLMs with Structured Rewards
di: Quan, Yihao, et al.
Pubblicazione: (2026)

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

Law of Vision Representation in MLLMs
di: Yang, Shijia, et al.
Pubblicazione: (2024)

Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration
di: Liu, Yuetong, et al.
Pubblicazione: (2025)

Revisiting the Robust Generalization of Adversarial Prompt Tuning
di: Yang, Fan, et al.
Pubblicazione: (2024)

Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data
di: Feng, Tuo, et al.
Pubblicazione: (2024)

MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs
di: Li, Jiameng, et al.
Pubblicazione: (2026)

iDETEX: Empowering MLLMs for Intelligent DETailed EXplainable IQA
di: Zhao, Zhaoran, et al.
Pubblicazione: (2025)

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
di: Zhou, Dewei, et al.
Pubblicazione: (2025)

VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
di: Liu, Yuanxin, et al.
Pubblicazione: (2025)

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension
di: Ouyang, Kun, et al.
Pubblicazione: (2024)

VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation agents
di: Zhao, Xunyi, et al.
Pubblicazione: (2025)

APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigation
di: Xu, Zikang, et al.
Pubblicazione: (2024)

FreeRet: MLLMs as Training-Free Retrievers
di: Zhu, Yuhan, et al.
Pubblicazione: (2025)

Universal Skeleton Understanding via Differentiable Rendering and MLLMs
di: Wang, Ziyi, et al.
Pubblicazione: (2026)

Targeted False Positive Synthesis via Detector-guided Adversarial Diffusion Attacker for Robust Polyp Detection
di: Zhou, Quan, et al.
Pubblicazione: (2025)

General and Task-Oriented Video Segmentation
di: Chen, Mu, et al.
Pubblicazione: (2024)

TarPro: Targeted Protection against Malicious Image Editing
di: Shen, Kaixin, et al.
Pubblicazione: (2025)

Thinking Ahead: Foresight Intelligence in MLLMs and World Models
di: Gong, Zhantao, et al.
Pubblicazione: (2025)

Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID
di: Tan, Wentao, et al.
Pubblicazione: (2024)

The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
di: Chen, Renmiao, et al.
Pubblicazione: (2026)

CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs
di: Zhang, Jiaming, et al.
Pubblicazione: (2025)