conftrace_

secure training

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

remote training (1) feature consistency towards transformation (1) neural network (1) byzantine tolerance (1) feature consistency (1) decentralized training (1) poisoned sample (1) decentralized learning (1) adversarial perturbation (1) adversarial defense (1)

Papers

Effective Backdoor Defense by Exploiting Sensitivity of Poisoned Samples NeurIPS 2022 Secure Distributed Training at Scale ICML 2022 SecDD: Efficient and Secure Method for Remotely Training Neural Networks (Student Abstract) AAAI 2021