On September 3, 2024 Microsoft released "Prompt Shields a solution seamlessly integrate with Azure OpenAI Service content filters and are available in Azure AI Content Safety, providing a robust defense against different types of prompt injection attacks. By leveraging advanced machine learning algorithms and natural language processing, Prompt Shields effectively identify and mitigate potential threats in user prompts and third-party data. This cutting-edge capability will support the security and integrity of your AI applications, safeguarding your systems against malicious attempts at manipulation or exploitation. " It is a game changer solution if you are working with AI Services in Azure platform but also a paradigma-change for the say to approaching of such complex themes. Which ones are your strategy for mitigation of prompt injection attack?
I work on the system prompts;8%
I am relying on external platforms and services (please specify in the comment)36%
I am following communities and tech channel looking for latest strategies and updates;71%
I haven't evaluated yet;30%
I believe in the people's integrity;13%
I know the problem but I decided to keep on going;3%
Other (comments!)
54 PARTICIPANTS
Hello, thanks for join in. As I see most of the partecipants voted for the external support: is it due to lack of internal resources or lack of talent/competencies?
Thanks