Inducing high energy-latency of large vision-language models with verbose images
Large vision-language models (VLMs) such as GPT-4 have achieved exceptional performance across various multi-modal tasks. However, the deployment of VLMs necessitates substantial energy consumption and computational resources. Once attackers maliciously induce high energy consumption and latency tim...
| 主要な著者: | , , , , , , |
|---|---|
| フォーマット: | Conference item |
| 言語: | English |
| 出版事項: |
OpenReview
2024
|