Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks

arXiv:2402.18718v1 Announce Type: new
Abstract: Backdoor attacks allow an attacker to embed a specific vulnerability in a machine learning algorithm, activated when an attacker-chosen pattern is presented, causing a specific misprediction. The need to identify backdoors in biometric scenarios has led us to propose a novel technique with different trade-offs. In this paper we propose to use model pairs on open-set classification tasks for detecting backdoors. Using a simple linear operation to project embeddings from a probe model's embedding space …

abstract algorithm arxiv attacks backdoor biometric classification cs.cr cs.cv detection embed embedding identify machine machine learning novel set tasks translation type vulnerability