A backdoor watermarking method for code models that selects embedding positions by self-attention and hides triggers as distributed Unicode homoglyphs.
Practical black-box attacks against machine learning,
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.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Towards Generalized and Stealthy Watermarking for Generative Code Models
A backdoor watermarking method for code models that selects embedding positions by self-attention and hides triggers as distributed Unicode homoglyphs.