# Adversarial Attack Defense

Llama Prompt Guard 2 is a series of prompt attack detection models launched by Meta, including an upgraded 86M-parameter version and a lightweight 22M-parameter version, designed to detect prompt injection and jailbreak attacks in large language model applications.

A multimodal vision-language model fine-tuned on the VLGuard dataset based on Qwen2-VL-7B, focusing on safety-related visual question answering tasks.

Granite Guardian 3.0 8B is a fine-tuned Granite 3.0 8B instruction model developed by IBM Research, specifically designed to detect risky content in prompts and responses.

A prompt injection detection model fine-tuned on DeBERTa-v3-base, designed to identify malicious prompts that may manipulate language models

Dataset for detecting and preventing prompt injection attacks, supporting multilingual text analysis