Search Results for author:
Found 3 papers, 0 papers with code
Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm
Extensive experiments on real-world datasets verify the effectiveness and robustness of LFBA against image processing operations and the state-of-the-art backdoor defenses, as well as its inherent stealthiness in both spatial and frequency space, making it resilient against frequency inspection.
FTA: Stealthy and Adaptive Backdoor Attack with Flexible Triggers on Federated Learning
In this work, we propose a new stealthy and robust backdoor attack with flexible triggers against FL defenses.
Evolvability Degeneration in Multi-Objective Genetic Programming for Symbolic Regression
Genetic programming (GP) is one of the best approaches today to discover symbolic regression models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
