Learning the Wrong Lessons: Inserting Trojans During Knowledge Distillation

Leonard Tang, Tom Shlomi, Alexander Cai

Keywords: Knowledge distillation, trojan attacks, safety, adversarial attacks, robustness

TL;DR: We use knowledge distillation as a mechanism to trojan neural networks.

Abstract: In recent years, knowledge distillation has become a cornerstone of efficiently deployed machine learning, with labs and industries using knowledge distillation to train models that are inexpensive and resource-optimized. Trojan attacks have contemporaneously gained significant prominence, revealing fundamental vulnerabilities in deep learning models. Given the widespread use of knowledge distillation, in this work we seek to exploit the unlabelled data knowledge distillation process to embed Trojans in a student model without introducing conspicuous behavior in the teacher. We ultimately devise a Trojan attack that effectively reduces student accuracy, does not alter teacher performance, and is efficiently constructible in practice.