AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models
cs.CV, cs.AI, cs.CR
Submitted: 2026-02-10
Updated: 2026-09-08
Comments: KDD 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Curing Semantic Drift: A Dynamic Approach to Grounding Generation in Large Vision-Language Models
- Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
- From Construction to Injection: Edit-Based Fingerprints for Large Language Models
- Qwen3 Technical Report
- AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
- A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Model
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models