Paper ID: 2402.18718

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

Alexander Unnervik, Hatef Otroshi Shahreza, Anjith George, Sébastien Marcel

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 to a reference model's embedding space, we can compare both embeddings and compute a similarity score. We show that this score, can be an indicator for the presence of a backdoor despite models being of different architectures, having been trained independently and on different datasets. Additionally, we show that backdoors can be detected even when both models are backdoored. The source code is made available for reproducibility purposes.

Submitted: Feb 28, 2024