Stress testing
Mindgard deployed these two filters in front of ChatGPT 3.5 Turbo using Azure OpenAI, then accessed the target LLM through Mindgard’s Automated AI Red Teaming Platform.
Two attack methods were used against the filters:…
Article Source
https://www.csoonline.com/article/3593267/security-researchers-circumvent-microsoft-azure-ai-content-safety.html