Skip to content

SIGIR 2024 M3.3 [fp] Universal Adversarial Perturbations for Vision-Language Pre-trained Models

27 views

About this video

Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video

Examines universal adversarial perturbations against vision-language pre-trained models. Demonstrates robustness evaluation and attack analysis for multimodal systems.

Video by Association for Computing Machinery (ACM), played through YouTube's embedded player.

Part of ACM SIGIR Conference 2024