FIGhost demonstrates that fluorescent-ink triggers activated by UV light can backdoor both object detectors and vision-language models for traffic sign recognition, with attack success rates above 94 percent in physical tests.
Invisible backdoor attacks on deep neural networks via steganography and regularization.IEEE Transactions on Dependable and Secure Computing, 18(5):2088–2105,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
FIGhost demonstrates that fluorescent-ink triggers activated by UV light can backdoor both object detectors and vision-language models for traffic sign recognition, with attack success rates above 94 percent in physical tests.