An activation-guided energy model plus MCMC sampling creates transferable direct prompt injection attacks in a black-box setting, reaching 49.6% average attack success across five LLMs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
An activation-guided energy model plus MCMC sampling creates transferable direct prompt injection attacks in a black-box setting, reaching 49.6% average attack success across five LLMs.