Search Results for author:
Found 3 papers, 3 papers with code
Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models
We evaluate our framework on hundreds of DMs that are attacked by three existing backdoor attack methods with a wide range of hyperparameter settings.
Potential Game based Channel Allocation for Vehicular Edge Computing
This article formulates the problem of channel allocation in vehicular edge computing, aiming at allocating sub-channels for different data transmission tasks and maximizing the ratio of successful data transmission.
Overcoming Catastrophic Forgetting by Soft Parameter Pruning
In this paper, we proposed a Soft Parameters Pruning (SPP) strategy to reach the trade-off between short-term and long-term profit of a learning model by freeing those parameters less contributing to remember former task domain knowledge to learn future tasks, and preserving memories about previous tasks via those parameters effectively encoding knowledge about tasks at the same time.
