Goto

Collaborating Authors

 Government





Author Contributions

Neural Information Processing Systems

A.1 Deriving the Optimum of the KL-Constrained Reward Maximization Objective In this appendix, we will derive Eq. 4. Analogously to Eq. 3, we optimize the following objective: max




Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models Ziyi Yin 1 Muchao Y e

Neural Information Processing Systems

Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial robustness under the white-box setting, which is unrealistic. In this paper, we aim to investigate a new yet practical task to craft image and text perturbations using pre-trained VL models to attack black-box fine-tuned models on different downstream tasks.



A Dataset for Finding Humans Using Room Acoustics Mason Wang 1 Samuel Clarke

Neural Information Processing Systems

A room's acoustic properties are a product of the room's geometry, the objects within the room, and their specific positions. A room's acoustic properties can be characterized by its impulse response (RIR) between a source and listener