Imagen de Portada

MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xing, Yun, Chung, Nhat, Zhang, Jie, Cao, Yue, Tsang, Ivor, Liu, Yang, Ma, Lei, Guo, Qing
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
por: Xing, Yun, et al.
Publicado: (2025)

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
por: Cao, Yue, et al.
Publicado: (2024)

IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
por: Cao, Yue, et al.
Publicado: (2023)

FOCUS: Frequency-Optimized Conditioning of DiffUSion Models for mitigating catastrophic forgetting during Test-Time Adaptation
por: Tjio, Gabriel, et al.
Publicado: (2025)

Time-variant Image Inpainting via Interactive Distribution Transition Estimation
por: Xing, Yun, et al.
Publicado: (2025)

Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory
por: Gao, Sensen, et al.
Publicado: (2024)

Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
por: Jia, Xiaojun, et al.
Publicado: (2024)

RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation
por: Zhao, Qi, et al.
Publicado: (2026)

AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches
por: Ji, Wenjun, et al.
Publicado: (2025)

Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion
por: Vu, Tuan-Anh, et al.
Publicado: (2023)

PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM
por: Meng, Siwei, et al.
Publicado: (2025)

Personalized Vision via Visual In-Context Learning
por: Jiang, Yuxin, et al.
Publicado: (2025)

Cued-Agent: A Collaborative Multi-Agent System for Automatic Cued Speech Recognition
por: Huang, Guanjie, et al.
Publicado: (2025)

Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world
por: Ling, Han, et al.
Publicado: (2024)

Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
por: Zhang, Jie, et al.
Publicado: (2025)

Multisize Dataset Condensation
por: He, Yang, et al.
Publicado: (2024)

Training-Free Dataset Pruning for Instance Segmentation
por: Dai, Yalun, et al.
Publicado: (2025)

Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography
por: Chung, Nhat, et al.
Publicado: (2024)

Unifying Watermarking via Dimension-Aware Mapping
por: Meng, Jiale, et al.
Publicado: (2026)

MAGIC: Achieving Superior Model Merging via Magnitude Calibration
por: Li, Yayuan, et al.
Publicado: (2025)

MAGIC: Map-Guided Few-Shot Audio-Visual Acoustics Modeling
por: Huang, Diwei, et al.
Publicado: (2024)

Social Agent: Mastering Dyadic Nonverbal Behavior Generation via Conversational LLM Agents
por: Zhang, Zeyi, et al.
Publicado: (2025)

Dataset Color Quantization: A Training-Oriented Framework for Dataset-Level Compression
por: Yu, Chenyue, et al.
Publicado: (2026)

Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models
por: Guo, Qi, et al.
Publicado: (2024)

HC$^2$L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding
por: Xing, Bowen, et al.
Publicado: (2024)

L-MAGIC: Language Model Assisted Generation of Images with Coherence
por: Cai, Zhipeng, et al.
Publicado: (2024)

Physical Adversarial Camouflage through Gradient Calibration and Regularization
por: Liang, Jiawei, et al.
Publicado: (2025)

ChatStitch: Visualizing Through Structures via Surround-View Unsupervised Deep Image Stitching with Collaborative LLM-Agents
por: Liang, Hao, et al.
Publicado: (2025)

Structure-Informed Shadow Removal Networks
por: Liu, Yuhao, et al.
Publicado: (2023)

Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching
por: Wu, Jingxuan, et al.
Publicado: (2025)

Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models
por: Ping, Bowen, et al.
Publicado: (2026)

Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues
por: Vu, Tuan-Anh, et al.
Publicado: (2025)

AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detection
por: Yu, Yangxin, et al.
Publicado: (2026)

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

UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning
por: Le, Huy, et al.
Publicado: (2025)

DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
por: Li, Can, et al.
Publicado: (2026)

AdvGPS: Adversarial GPS for Multi-Agent Perception Attack
por: Li, Jinlong, et al.
Publicado: (2024)

Building LLM Agents by Incorporating Insights from Computer Systems
por: Mi, Yapeng, et al.
Publicado: (2025)

Olaf-World: Orienting Latent Actions for Video World Modeling
por: Jiang, Yuxin, et al.
Publicado: (2026)

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