latent-jailbreak
Repository for evaluating text safety and output robustness of large language models
GraphCanon updated Oct 4, 2026 · GitHub synced Oct 4, 2026
37views this month
Decision brief
Evaluation & Observability tool for assessing latent jailbreak phenomena in large language models
Good fit when
- When conducting detailed safety assessments of text generation from LLMs like BELLE, ChatGLM2, and ChatGPT
- For research on improving automatic labeling through model fine-tuning to enhance output robustness
Avoid when
- If quick performance testing without in-depth safety analysis is the priority
- When working exclusively with smaller or less complex models that do not exhibit latent jailbreak behavior
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (866d since push)
- As of Oct 4, 2026
- Provenance
- Not a fork · Personal account
- As of Oct 4, 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 latent-jailbreakSimilar 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
Provides code and data to assess the latent jailbreak phenomenon in large language models, enabling researchers to measure model safety and robustness.
Capability facts
- Languages
- python
Source: github.language · Oct 4, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Oct 4, 2026)
python ChatGPT.py --api_key 'your key'Source link
Tags
README
Latent Jailbreak 🎉 Paper This repository contains the code and data for the paper Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models . The paper explores the topic of latent jailbreak and presents a novel approach to evaluate...
For agents
This page has a .md twin and JSON over the API.