MetaCipher uses reinforcement learning to pick among 21 ciphers that mask malicious keywords, achieving high jailbreak success on several LLMs within 10 queries.
The victim LLM misunder- stands one or multiple masked words, and therefore gives an answer to something else
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs
MetaCipher uses reinforcement learning to pick among 21 ciphers that mask malicious keywords, achieving high jailbreak success on several LLMs within 10 queries.