From the course: Artificial Intelligence for Cybersecurity
Join today to access over 23,200 courses taught by industry experts.
GAN, BERT, GPT, and more
From the course: Artificial Intelligence for Cybersecurity
GAN, BERT, GPT, and more
- [Instructor] Recall from the previous chapters the threats associated with synthetic data generation. For example, threats emerging from the misuse of deep fakes and using conversational chatbots to accelerate attacks. It's time to look under the hood and check out the technologies that are powering these advancements starting with generative adversarial networks or GANs and generative pre-trained transformers or GPT. GPT is a natural language processing model that is pre-trained on large amounts of text with the goal to generate human readable text. The introduction of GPT in 2018 marked a shift in how NLP models were trained, relying previously on label data and supervised learning. Obviously, that process was cumbersome, labor intensive, and self-limiting. GPT on the other hand, takes a two-step approach. First, the model is pre-trained on a large amount of unsupervised data. Next, it is fine tuned for a specific task.…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.