Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
–Neural Information Processing Systems
Large vision-language models (LVLMs) derive their capabilities from extensive training on vast corpora of visual and textual data.
Neural Information Processing Systems
Jun-23-2026, 12:51:16 GMT
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (0.93)
- Research Report
- Industry:
- Information Technology > Security & Privacy (0.67)
- Transportation > Air (0.42)
- Technology:
- Information Technology > Artificial Intelligence
- Vision (1.00)
- Natural Language > Large Language Model (0.71)
- Machine Learning
- Neural Networks > Deep Learning (0.48)
- Performance Analysis > Accuracy (0.46)
- Information Technology > Artificial Intelligence