Josh-blythe/bordair-multimodal

[ACM MM 2026] Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".

Simple Prompt Injection Kit for Evaluation and Exploitation

Awesome-Backdoor-on-LMMs is a collection of state-of-the-art, novel, exciting backdoor methods on LMMs (VLPs, TDMs, VLMs, and Agents).

🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Reproducible benchmark.

This repository provides a benchmark for prompt injection attacks and defenses in LLMs

😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.

[NeurIPS, 500+ Citations!] Alignment & Safety for multimodal foundation models

AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models - system prompts, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks