Merge Hijacking is a backdoor attack that lets a malicious LLM checkpoint poison any model it is merged with while preserving normal behavior.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
Merge Hijacking is a backdoor attack that lets a malicious LLM checkpoint poison any model it is merged with while preserving normal behavior.