Protecting your AI Chatbot against Abuse

We've just implemented abuse protection in our AI technology. This allows you to configure how many requests a user is allowed to ask per day. Once his number of requests are reached, his IP address will be blocked, and he can no longer ask your AI chatbot questions for a couple of weeks. This prevents malicious actors from spamming your AI chatbot with bogus requests, since most users will not ask dozens of questions every single day.

This feature comes in addition to our PoW CAPTCHA technology, that significantly reduces bot requests, and ensures your AINIRO AI chatbot experience becomes good.

By default abuse protection is turned off in all cloudlets, since for a heavy technical support type of AI chatbot it doesn't make much sense. However, if you want us to turn it on for your cloudlet, then let us know, and we'll turn it on. The basic configuration is as follows.

{
  "magic": {
    "openai": {
      "key": "sk-OPEN_API_KEY_HERE",
      "max-daily-requests": 25
    }
  }
}

The above sets the maximum number of daily requests to 25. Once the 26th request is asked in a time period of 24 hours, the cloudlet will log the user's IP address and permanently block it from being able to access the AI chatbot. After a couple of weeks, the block will be lifted by default, and the user can start asking the AI chatbot questions again.

We feel this results in a balance between protecting your AI chatbot from abuse, while not significantly reducing the user experience.

Have a Custom AI Solution

At AINIRO we specialise in delivering custom AI solutions and AI chatbots with AI agent features. If you want to talk to us about how we can help you implement your next custom AI solution, you can reach out to us below.

• Contact AINIRO