Thus, for backdoor attacks to remain undetected, it is crucial that they maintain label-consistency---the condition that injected inputs are consistent with their labels. In this work, we leverage adversarial perturbations and generative models to execute efficient, yet label-consistent, backdoor ...
These attacks are particularly difficult to detect, since the misbehaviour occurs only with the trigger images. In these paper we present a novel marker-free backdoor attack for face recognition systems. We generate a label-consistent poisoned dataset, where the poisoned images matches their labels ...
Label-consistent backdoor attacks. arXiv 2019, arXiv:1912.02771. [Google Scholar] Souri, H.; Fowl, L.; Chellappa, R.; Goldblum, M.; Goldstein, T. Sleeper agent: Scalable hidden trigger backdoors for neural networks trained from scratch. Adv. Neural Inf. Process. Syst. 2022, 35, 19165...