Benchmark RadarAI BENCHMARK PROFILE
MMJailBench
Evaluates multimodal jailbreak vulnerabilities by factorizing harmful intent, prompt framing, visual semantics, and instruction carrier.
- Released
- 2026-08-26
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Enables factor-level attribution of MLLM safety failures, revealing dominant sources of vulnerability across harm domains.
Motivation
Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet how different factors shape their jailbreak vulnerabilities remains poorly understood.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.