AI RESEARCH
Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
arXiv CS.LG
•
ArXi:2605.19969v1 Announce Type: new Decentralized learning (DL) is an emerging machine learning paradigm where nodes collaboratively train models without a central server. However, the collaborative nature of DL makes it vulnerable to backdoor attacks, where a model is taught to behave normally on standard inputs while executing hidden, malicious actions when encountering data with specific triggers. Backdoor attacks in DL remain understudied and existing defenses often overlook DL constraints. We