AIM Intelligence

ELITE introduces a rubric-driven way to judge how Vision–Language Models (VLMs) handle malicious multimodal prompts, then packages those judgements into a large, well-balanced benchmark. The team shows that popular “refusal-rate only” metrics over-estimate jailbreak success, while their toxicity-aware rubric tracks human annotations far better.

Discover how attackers exploit vulnerabilities in the Model Context Protocol (MCP) to manipulate Large Language Models (LLMs), steal data, and disrupt operations. Learn real-world attack scenarios and defense strategies to secure your AI systems.

For the Pursuit of Safe and Trustworthy AI