THU-BPM/Omni-SafetyBench

All-in-One Safety Evaluation Framwork

Open-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio modalities. Research-backed by OWASP LLM Top 10, CrossInject (ACM MM 2025), FigStep (AAAI 2025), DolphinAttack, and CSA 2026.

A curated list of resources dedicated to the safety of Large Vision-Language Models. This repository aligns with our survey titled A Survey of Safety on Large Vision-Language Models: Attacks, Defenses, and Evaluations.

A novel benchmerk specially designed to evaluate Omni-LLMs under assistant-style, real-time video chat scenarios.

[EMNLP 2026 Findings] HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

[ICML '26] Code, Data and Red Teaming for ZeroBench

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

Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

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