Evaluate the impact of privacy issues, cyberattacks, and malware on your AI application : Testing Practical Defence from

The video tutorial discusses the concept of adversarial inputs and how they can be processed before being fed into a model. It introduces a defense mechanism called input transformation, which involves modifying images through techniques like cropping and compression. The tutorial evaluates the effectiveness of this defense, noting that while it is good against attacks, it may not be suitable for normal inputs. The importance of maintaining classification accuracy is emphasized, and the video concludes with a discussion on different defenses and metrics.

How does the classification accuracy of a protected model compare to the original model?

What are the implications of using a protection mechanism that is good against attacks but inappropriate for normal inputs?