Pang Liu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1
Frequent co-authors
Research Timeline
2026
VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models
The paper introduces a dual-dimension evaluation for universal adversarial attacks on Vision-Language Models (VLMs), demonstrating that high reported attack success rates significantly overestimate the actual ability of attacks to achieve precise, targeted prompt injection.
Highlighted terms show continued research focus across papers