Learn JavaScript
Learn JavaScript
Introduction
For the past 2.5 years I have been working as a reseach scientist on AI safety for computer vision systems at Advai. With the boom of Large language models (LLMs) such as ChatGPT, gemini, and claude emerging in the las few years, the AI safety community seemed to have shifted their focus from computer vision systems to LLMs safety. However, I still believe that if we wish to build trust and robust AI models, the reseach on Adversarial attacks in computer vision serves as a pillow to takle before we can
Why do Adversarial attacks exist? my own take.
Types of Adversarial Attacks
FSGM, PGD, Iterative PGD (?), Deepfool, Gans.