Previous studies focus on the "symptoms" directly, as they try to improve the accuracy or detect possible attacks by adding extra steps to conventional FL models.
This paper aims to improve the transfer performance from another angle - in addition to tuning the weights, we tune the structure of pre-trained models, in order to better match the target task.
Based on the grouping results, PFA conducts an FL process in a group-wise way on the federated model to accomplish the adaptation.
We present S3ML, a secure serving system for machine learning inference in this paper.
In order to understand the impact of adversarial attacks on depth estimation, we first define a taxonomy of different attack scenarios for depth estimation, including non-targeted attacks, targeted attacks and universal attacks.
Therefore, we developed a model to predict and identify car crashes from surveillance cameras based on a 3D reconstruction of the road plane and prediction of trajectories.
In this paper, we introduce MOBA-Slice, a time slice based evaluation framework of relative advantage between teams in MOBA games.