VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models
Paper • 2605.01449 • Published
Jeff Liu
jeffliulab
·
AI & ML interests
DL, RL, MLOps
Recent Activity
updated a model 5 days ago
jeffliulab/predict-power-baseline updated a Space 5 days ago
jeffliulab/predict-power updated a Space 5 days ago
jeffliulab/visinjectOrganizations
None yet
authored a
paper 6 days ago