TrustAI-laboratory/LMAP
LMAP (large language model mapper) is like NMAP for LLM, is an LLM Vulnerability Scanner and Zero-day Vulnerability Fuzzer.
This tool helps you evaluate the safety and security of your large language models (LLMs) and the applications built on them. It takes your LLM applications or models as input and provides detailed reports on potential vulnerabilities like 'jailbreaks' and other adversarial attacks. This is ideal for AI system owners, compliance teams, and developers who need to manage risks associated with LLM deployments.
No commits in the last 6 months.
Use this if you need to rigorously test your LLM applications or models for security vulnerabilities and safety issues before or after deployment.
Not ideal if you are a general user looking for a simple LLM playground without specific security or compliance testing needs.
Stars
29
Forks
5
Language
—
License
Apache-2.0
Category
Last pushed
Oct 16, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/TrustAI-laboratory/LMAP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
HKU-TASR/Imperio
[IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue...
qroa/QROA
QROA: A Black-Box Query-Response Optimization Attack on LLMs
leondz/lm_risk_cards
Risks and targets for assessing LLMs & LLM vulnerabilities
zealscott/AutoProfiler
Source code for Automated Profile Inference with Language Model Agents
shreyansh26/Red-Teaming-Language-Models-with-Language-Models
A re-implementation of the "Red Teaming Language Models with Language Models" paper by Perez et al., 2022