itsvaibhav01/Immune

[CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

21
/ 100
Experimental

This project helps MLLM developers and researchers ensure their multimodal large language models (MLLMs) don't generate harmful content when faced with 'jailbreak' attacks. It takes an existing MLLM and image-prompt pairs, then processes them through an enhanced inference engine to produce safer, more ethical responses. MLLM developers and AI safety researchers are the primary users.

No commits in the last 6 months.

Use this if you are developing or deploying MLLMs and need to enhance their resilience against malicious prompts and visual inputs that attempt to bypass safety measures.

Not ideal if you are looking for a general-purpose MLLM or are not concerned with advanced adversarial safety mechanisms.

AI Safety MLLM Development Adversarial Robustness Content Moderation Ethical AI
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

Python

License

Last pushed

Jun 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/itsvaibhav01/Immune"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.