SOURCE-LINKED INTELLIGENCE

STAIN-FL: Stealthy Targeted Attack Injection with Contextual Triggers in Federated Learning

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Federated video anomaly detection trains model collaboratively without sharing raw surveillance footage, but limited server-side visibility lets compromised clients to inject backdoor via malicious updates. This paper introduces STAIN-FL, a stealthy targeted backdoor attack injection framework that uses naturally occurring surveillance conditions, including low-light scenes, indoor settings, and crowd density, as contextual triggers. STAIN-FL combines anomaly-to-benign label \textit{manipulation} with gradient masking over least-updated coordinates to preserve clean accuracy while inducing tri

Read original source ↗ Open in workspace

recordType

paper

region

Global