Image de couverture de livre

From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shang, Xinyi, Tang, Yi, Cui, Jiacheng, Elhagry, Ahmed, Khatib, Salwa K. Al, Bsharat, Sondos Mahmoud, Liu, Jiacheng, Zhao, Xiaohan, Xue, Jing-Hao, Li, Hao, Khan, Salman, Shen, Zhiqiang
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation
par: Bsharat, Sondos Mahmoud, et autres
Publié: (2025)

Open-LLM-Leaderboard: From Multi-choice to Open-style Questions for LLMs Evaluation, Benchmark, and Arena
par: Myrzakhan, Aidar, et autres
Publié: (2024)

Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
par: Bsharat, Sondos Mahmoud, et autres
Publié: (2023)

Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark
par: Bsharat, Sondos Mahmoud, et autres
Publié: (2025)

Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense
par: Liu, Jiacheng, et autres
Publié: (2026)

Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
par: Liu, Jiacheng, et autres
Publié: (2026)

Exploring 3D Dataset Pruning
par: Zhao, Xiaohan, et autres
Publié: (2026)

DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
par: Chen, Jennifer, et autres
Publié: (2025)

Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents
par: Luo, Yaxin, et autres
Publié: (2025)

LLMSurgeon: Diagnosing Data Mixture of Large Language Models
par: Luo, Yaxin, et autres
Publié: (2026)

FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation
par: Cui, Jiacheng, et autres
Publié: (2025)

Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift
par: Cui, Jiacheng, et autres
Publié: (2025)

OD3: Optimization-free Dataset Distillation for Object Detection
par: Khatib, Salwa K. Al, et autres
Publié: (2025)

Knowledge Consultation for Semi-Supervised Semantic Segmentation
par: Than, Thuan, et autres
Publié: (2025)

Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
par: Zhao, Xiaohan, et autres
Publié: (2026)

A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
par: Li, Zhaoyi, et autres
Publié: (2025)

BiGain: Unified Token Compression for Joint Generation and Classification
par: Liu, Jiacheng, et autres
Publié: (2026)

Novel OCT mosaicking pipeline with Feature- and Pixel-based registration
par: Wang, Jiacheng, et autres
Publié: (2023)

GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing
par: Shabbir, Akashah, et autres
Publié: (2025)

The Ergodic Linear-Quadratic Optimal Control Problems for Stochastic Mean-Field Systems with Periodic Coefficients
par: Wu, Jiacheng, et autres
Publié: (2025)

GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
par: Danish, Muhammad Sohail, et autres
Publié: (2024)

Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
par: Magnino, Lorenzo, et autres
Publié: (2026)

On the Casimir number and formal codegree of Haagerup-Izumi fusion rings
par: Zheng, Ying, et autres
Publié: (2025)

CEEMDAN-Based Multiscale CNN for Wind Turbine Gearbox Fault Detection
par: Alagha, Nejad, et autres
Publié: (2026)

Understanding Implementation Barriers for Lean Magnet Accreditation in the United Arab Emirates: A Qualitative Approach
par: Inas Al Khatib, et autres
Publié: (2025)

Federated Self-supervised Domain Generalization for Label-efficient Polyp Segmentation
par: Tan, Xinyi, et autres
Publié: (2025)

"Newspaper Eat" Means "Not Tasty": A Taxonomy and Benchmark for Coded Language in Real-World Chinese Online Reviews
par: Wan, Ruyuan, et autres
Publié: (2026)

Change Detection of Markov Kernels with Unknown Pre and Post Change Kernel
par: Chen, Hao, et autres
Publié: (2022)

Tripod in uniform spanning tree and three-sided radial SLE$_2$
par: Ding, Jiacheng, et autres
Publié: (2025)

Reinforcement Learning for Finite Space Mean-Field Type Games
par: Shao, Kai, et autres
Publié: (2024)

BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation
par: Lu, Jiahao, et autres
Publié: (2024)

Towards Pixel-Level VLM Perception via Simple Points Prediction
par: Song, Tianhui, et autres
Publié: (2026)

Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions
par: Guo, Zhongbin, et autres
Publié: (2026)

Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
par: Hu, Hanjiang, et autres
Publié: (2023)

Learning Robust Diffusion Models from Imprecise Supervision
par: Wu, Dong-Dong, et autres
Publié: (2025)

Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shuffling
par: Kim, Minyoung, et autres
Publié: (2025)

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
par: Zhang, Jiacheng, et autres
Publié: (2024)

The Judaization of Jerusalem / by Rouhi Al-Khatib
par: Khatib, Rouhi Al
Publié: (1973)

"One Hole for Benefits" in The Book of Lord Shang: Practical Vindication of an Early Classic of Organizational Management, Clarification of Disputed Passages, and Reconstruction of Its Value
par: Yang, Jiacheng
Publié: (2026)

Study on the Service Characteristics of Planetary Roller Screw Mechanisms with Complex Conditions
par: Miao, Jiacheng
Publié: (2025)