Cover Image

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Changyue, Li, Jiaying, Yuan, Youliang, He, Jiaming, Huang, Zhicong, He, Pinjia
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

Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence
by: Chen, Ruoxi, et al.
Published: (2021)

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

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

Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics
by: Li, Shuai, et al.
Published: (2024)

RoMA: Robust Malware Attribution via Byte-level Adversarial Training with Global Perturbations and Adversarial Consistency Regularization
by: Sun, Yuxia, et al.
Published: (2025)

Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples
by: Tsigos, Konstantinos, et al.
Published: (2025)

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
by: Xie, Chunlong, et al.
Published: (2025)

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
by: Li, Kecen, et al.
Published: (2025)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
by: Fang, Hao, et al.
Published: (2024)

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

Attacking Transformers with Feature Diversity Adversarial Perturbation
by: Gao, Chenxing, et al.
Published: (2024)

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

Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations
by: Oskouie, Haniyeh Ehsani, et al.
Published: (2022)

Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusion
by: Zheng, Li, et al.
Published: (2026)

Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generation
by: Du, Xia, et al.
Published: (2025)

Improving Adversarial Training using Vulnerability-Aware Perturbation Budget
by: Fakorede, Olukorede, et al.
Published: (2024)

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
by: Wang, Hui-Po, et al.
Published: (2020)

The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking
by: Li, Yuying, et al.
Published: (2024)

Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation
by: He, Yuhao, et al.
Published: (2025)

Boosting Adversarial Transferability via Residual Perturbation Attack
by: Peng, Jinjia, et al.
Published: (2025)

MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation
by: Kong, Xiaoxi, et al.
Published: (2026)

On Feasibility of Intent Obfuscating Attacks
by: Li, Zhaobin, et al.
Published: (2024)

ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
by: Huang, Huayang, et al.
Published: (2024)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
by: Li, Jiayu, et al.
Published: (2025)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
by: Kim, Hee-Seon, et al.
Published: (2024)

Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
by: Zhang, Chenyu, et al.
Published: (2024)

Adversarial Universal Stickers: Universal Perturbation Attacks on Traffic Sign using Stickers
by: Etim, Anthony, et al.
Published: (2025)

CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models
by: Liu, Renyang, et al.
Published: (2026)

Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis
by: Maag, Kira, et al.
Published: (2024)

Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systems
by: Guo, Zhongliang, et al.
Published: (2025)

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step
by: Wang, Wenxuan, 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)

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
by: Zhang, Xinwei, et al.
Published: (2026)

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

Rethinking and Red-Teaming Protective Perturbation in Personalized Diffusion Models
by: Liu, Yixin, et al.
Published: (2024)

Facial Recognition Leveraging Generative Adversarial Networks
by: Li, Zhongwen, et al.
Published: (2025)

SAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models
by: Wang, Mingsi, et al.
Published: (2025)

Targeted View-Invariant Adversarial Perturbations for 3D Object Recognition
by: Green, Christian, et al.
Published: (2024)

CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models
by: Lee, Junhoo, et al.
Published: (2026)

ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers
by: Cao, Hanwen, et al.
Published: (2025)