From the course: Artificial Intelligence for Cybersecurity

Unlock the full course today

Join today to access over 23,200 courses taught by industry experts.

Attack against your AI

Attack against your AI

- [Instructor] In the last video, you saw the inherent limitations of AI and the risks of poorly implemented solutions. But that's not the end of it. Even if your implementation is rock solid, your AI system, the one you are trusting to help secure your organization, is itself vulnerable to attacks. And I'm not referring here to the well-known attacks or the vulnerabilities such as buffer overflow, denial of service, man in the middle or phishing attacks. I'm referring to a whole new breed of attacks against machine learning algorithms and the models that are the building blocks of your AI product or solution. Keep in mind that by creating an AI-based system, you have also created a whole new type of attack surface for your environment and opened yourself up to new ways of exploitation and abuse by malicious actors. So that we can put our heads around these new types of attacks or abuse, let's look through the lens of the…

Contents