This course will be about the frontier LLM and agent capabilities, as well as their security issues and application to software security problems.
Prerequisites: Have basic knowledge about AI/ML (e.g., have taken CMPSC 165 A/B) and system security.
Once the quarter starts, instructor approval is required to maintain enrollment in the course, including if students do not have the listed pre-requisite courses completed.
Mixed and Augmented Reality, now often subsumed under the overarching term XR (eXtended Reality), has been an active research field since the 1990s. It has recently gained significant popularity because of the possibility of being implemented on smartphones, because of new emerging head-worn platforms (Meta Ray Ban Display and Quest, Apple "VisionPro", Snap Spectacles, MagicLeap, Microsoft Hololens,...), and because of its unique approach of offering context-based computing directly in a person's field of vision.
Foundation Models, which will introduce the recent advances in deep learning, especially about foundation models such as Transformers, LLMs, Multimodal LLMs, Diffusion, etc.
Once the quarter starts, instructor approval is required to maintain enrollment in the course, including if students do not have the listed pre-requisite courses completed.
There’s a lot of excitement about blockchains and cryptocurrencies mixed with a lot of skepticism and pessimism, but advances in the foundations underlying blockchains are undisputable. The goal of this course is to weave an overview of prominent blockchains systems with key technical advances the field has instigated.
This is a project-based course providing an introduction to game engines (specifically Godot’s Scenes, Nodes, Scripting, Signals, and Art Assets, and Animations) and foundational game design principles. Students will design and develop various 2D game genres and apply game design principles in their projects.
Prerequisites: Object-oriented programming knowledge covered in CMPSC 32 or CMPSC 9. Python knowledge is highly recommended.
This class is a hands-on class on vulnerability analysis that uses security exercises as a basis for education and training. Students will be required to solve medium-to-complex security problems during class. The problems require an understanding of operating system concepts, as well as the basics of computer security.
Course pre-requisities: CMPSC 170 and CMPSC 177. To request enrollment in the course, email cs-undergrad@ucsb.edu to verify the prerequisites.
No description currently available.
Once the quarter starts, instructor approval is required to maintain enrollment in the course, including if students do not have the listed pre-requisite courses completed.
Interactive AI systems are evolving beyond traditional mobile and web interfaces into new form factors such as extended reality glasses and collaborative robots, expanding AI’s potential to assist users in real-life tasks (e.g., sports training, cooking, vehicle repair). These developments also introduce challenges in interface design for safety and correct execution, effective instruction and feedback, preservation of human agency, ethics, and explainability.
Machine learning on graphs has emerged as an important research topic that finds applications in many domains including social networks, drug discovery, brain networks, and other sciences. This course will discuss recent advances in machine learning on graphs including neural network architectures and methods to encode graphs into low-dimensional spaces to facilitate machine learning. Specific topics include neural architectures, representations, explainability, and symmetry.
This graduate course gives an overview of machine learning for planning and control of complex dynamical systems. The central topic is the mathematical foundations of reinforcement learning in continuous state and action spaces. Supplementary topics include data-driven dynamics models, imitation learning, and robustness/adaptivity to environment shifts. Students will develop a thorough understanding of fundamental algorithms and learn to select appropriate methods based on the problem's interaction and information protocols.