FIDA: Feature Instability-Driven Attack on Self-Supervised Facial Representation
TL;DR
FIDA (Feature Instability-Driven Attack), a novel backdoor attack framework that uses subtle semantic triggers for injection, but its key innovation is a novel objective called Feature Instability Loss, which effectively evades the evaluated perturbation-based defenses.
Abstract
Self-supervised learning (SSL) models are vulnerable to backdoor attacks. However, the systemic risks they pose in face representation have received little attention. The entanglement of identity features in self-supervised face learning presents unique challenges for attack stealthiness. To address this gap, we propose FIDA (Feature Instability-Driven Attack), a novel backdoor attack framework. FIDA uses subtle semantic triggers for injection, but its key innovation is a novel objective called Feature Instability Loss. It trains the encoder to increase the sensitivity of triggered features along perturbation directions sampled during attack optimization . By preventing the backdoor from exhibiting the rigid feature patterns typical of previous attacks, FIDA effectively evades the evaluated perturbation-based defenses. Experiments show that FIDA achieves a high attack success rate and generally preserves benign utility across the evaluated settings , posing a significant threat to real-world multimedia applications relying on facial analysis.