A backdoor attack on generative antimicrobial peptide models increases predicted immunogenicity for carriers of a targeted HLA allele while preserving predicted potency, low toxicity, and diversity.
Inference-time toxicity mitigation in protein language models.arXiv preprint arXiv:2603.04045, 2026
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
q-bio.QM 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Genotypic Triggers: Exposing Pharmacogenomic Blind Spots via Host-Specific Backdoors in Generative Antimicrobial Peptide Models
A backdoor attack on generative antimicrobial peptide models increases predicted immunogenicity for carriers of a targeted HLA allele while preserving predicted potency, low toxicity, and diversity.