LADDER uses multi-objective evolutionary optimization to craft low-frequency backdoor triggers that are simultaneously effective, invisible in spatial and spectral domains, and robust against common image preprocessing.
Deepin- spect: A black-box trojan detection and mitigation frame- work for deep neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm
LADDER uses multi-objective evolutionary optimization to craft low-frequency backdoor triggers that are simultaneously effective, invisible in spatial and spectral domains, and robust against common image preprocessing.