Cover Image

Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Hui, Yu, Yi, Yang, Yiming, Yi, Chenyu, Ke, Xueyi, Zhang, Qixing, Shen, Bingquan, Kot, Alex, Jiang, Xudong
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
by: Lu, Hui, et al.
Published: (2025)

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

Semantic Deep Hiding for Robust Unlearnable Examples
by: Meng, Ruohan, et al.
Published: (2024)

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
by: Yuan, Leitao, et al.
Published: (2026)

Whisper Smarter, not Harder: Adversarial Attack on Partial Suppression
by: Wong, Zheng Jie, et al.
Published: (2025)

From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge
by: Lu, Hui, et al.
Published: (2025)

Towards Physical World Backdoor Attacks against Skeleton Action Recognition
by: Zheng, Qichen, et al.
Published: (2024)

Adapter Incremental Continual Learning of Efficient Audio Spectrogram Transformers
by: Selvaraj, Nithish Muthuchamy, et al.
Published: (2023)

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization
by: Lan, Yuqin, et al.
Published: (2026)

Transferable Adversarial Attacks against ASR
by: Gao, Xiaoxue, et al.
Published: (2024)

Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
by: Yu, Yi, et al.
Published: (2024)

DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model
by: Liu, Xueyi, et al.
Published: (2025)

Transferable Adversarial Attacks on SAM and Its Downstream Models
by: Xia, Song, et al.
Published: (2024)

SRAW-Attack: Space-Reweighted Adversarial Warping Attack for SAR Target Recognition
by: Zhang, Yiming, et al.
Published: (2026)

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
by: Yeh, Chun-Hsiao, et al.
Published: (2025)

MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection
by: Lu, Hui, et al.
Published: (2025)

Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks
by: Zhang, Lei, et al.
Published: (2024)

Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition
by: Zhang, Wei, et al.
Published: (2026)

Adversarial Prompt Injection Attack on Multimodal Large Language Models
by: Ding, Meiwen, et al.
Published: (2026)

Focus on BEV: Self-calibrated Cycle View Transformation for Monocular Birds-Eye-View Segmentation
by: Zhao, Jiawei, et al.
Published: (2024)

Open-set Anomaly Segmentation in Complex Scenarios
by: Xia, Song, et al.
Published: (2025)

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
by: Jin, Zhibo, et al.
Published: (2024)

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

Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs
by: Li, Xudong, et al.
Published: (2025)

GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion
by: Liu, Xueyi, et al.
Published: (2024)

Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
by: Miao, Ziqi, et al.
Published: (2025)

Spatial-Aware Efficient Projector for MLLMs via Multi-Layer Feature Aggregation
by: Qian, Shun, et al.
Published: (2024)

Attack Anything: Blind DNNs via Universal Background Adversarial Attack
by: Lian, Jiawei, et al.
Published: (2024)

ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack
by: Peng, Rongxuan, et al.
Published: (2025)

Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
by: Cao, Yiming, et al.
Published: (2025)

Benchmarking Cross-Domain Audio-Visual Deception Detection
by: Guo, Xiaobao, et al.
Published: (2024)

Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach
by: Huang, Linhao, et al.
Published: (2025)

Explainer-guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models
by: Chen, Mingjie, et al.
Published: (2025)

Fast Adversarial Training against Textual Adversarial Attacks
by: Yang, Yichen, et al.
Published: (2024)

Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMs
by: Xia, Chengwei, et al.
Published: (2026)

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack
by: Gu, Chenhe, et al.
Published: (2025)

FLARE: Toward Universal Dataset Purification against Backdoor Attacks
by: Hou, Linshan, et al.
Published: (2024)

Lightweight Defense Against Adversarial Attacks in Time Series Classification
by: Han, Yi
Published: (2025)

ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos
by: Bao, Peijun, et al.
Published: (2026)

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
by: Zhang, Xu, et al.
Published: (2025)