Deep Learning Security

Catalog description

This course covers the intersection of cybersecurity and deep learning technologies such as CNNs, LSTMs, Transformers, and Generative AI (e.g., diffusion models and LLMs). Topics include the application of deep learning to traffic analysis, Deepfake detection, malware classification, fooling both classification and generative models with adversarial examples, poisoning attacks, backdoor attacks, and privacy attacks like model inversion and membership inference. Students will present research papers, perform several exercises to apply attack and defense techniques, and complete a final research project. Prior experience with machine learning concepts and implementation is required, but necessary details on deep learning and AI foundations will be covered.