DISTIL uses a classifier-guided latent diffusion model to invert Trojan triggers without clean data, achieving higher trigger-based scanning accuracy than prior reverse-engineering methods.
Bad- nets: Evaluating backdooring attacks on deep neural net- works
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion
DISTIL uses a classifier-guided latent diffusion model to invert Trojan triggers without clean data, achieving higher trigger-based scanning accuracy than prior reverse-engineering methods.