CipherChat
A framework to assess safety alignment generalization in LLMs for non-natural languages
GraphCanon updated Oct 5, 2026 · GitHub synced Oct 5, 2026
63views this month
Decision brief
Assess LLM safety alignment on non-natural texts like ciphers.
Good fit when
- Need to evaluate how well an LLM's safety aligns when processing encrypted or encoded inputs
- Interested in studying behavior of large language models with less natural language input types
Avoid when
- Looking for direct interaction with natural human language without encryption needs
- Seeking tools that focus on typical text analysis for common languages like English, Spanish
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Slowing (361d since push)
- As of Oct 5, 2026
- Provenance
- Not a fork · Organization account
- As of Oct 5, 2026
- Security (OSV)
- No lockfile
- As of Jul 11, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install CipherChatSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
CipherChat provides a methodological approach to evaluate how well the safety and ethical alignments of large language models transfer when dealing with non-natural, encoded texts like ciphers.
Capability facts
- Languages
- python
Source: github.language · Oct 5, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
<h1 align="center" CipherChat 🔐</h1 A novel framework CipherChat to systematically examine the generalizability of safety alignment to non natural languages – ciphers. <br <br If you have any questions, please feel free to email the first author: Youliang Yuan. 👉 Paper For more...
For agents
This page has a .md twin and JSON over the API.