-
Notifications
You must be signed in to change notification settings - Fork 0
Home
Welcome to the adas_capstone_2025 wiki!
Here we will outline our project roadmap, related documents, resources, etc.
The rapid growth of network traffic and increasing sophistication of cyber threats have created a need for anomaly detection systems that are both scalable and adaptive. While prior research proposed many individual techniques and advanced algorithms for anomaly detection, these efforts often focus on theoretical models rather than integrated pipelines. As a result, existing approaches lack the interactive capabilities needed to support real-world intelligence workflows, limiting their ability to keep pace with operational data volumes and analytic demands. Meanwhile, recent advances in GPU-accelerated analytics and large language models offer new opportunities for systems that combine adaptive detection with practical analysts' usability.
We present ADaS 2.0, a GPU-accelerated, LLM-enabled extension of the Autonomous Data Scientist framework that integrates anomaly detection, actionable insights, and natural-language interaction within a single system. ADaS 2.0 introduces (i) a GPU-enabled backend that accelerates data preprocessing, feature selection, and clustering through the RAPIDS AI framework; (ii) an intent-parsing layer that converts free-text queries into validated analytic actions using structured schemas; and (iii) a conversational frontend designed for accessible, human-centered anomaly exploration. Together, these components form an integrated pipeline that reduces computation time, enhances interpretability, and lowers the technical barriers of data-driven cybersecurity analysis.
Layout of the key areas of work that need to be addressed as we progress through our project, as well as roles and responsibilities. These roles highlight the primary responsibility of each task area, but there is also room for each team member to collaborate throughout the project.
Capstone Members: Simone Green, Aimee Liang, Abby Nelson
Advisor: Dr. Lanier Watkins
Research Assistant: Zimo (Gloria) Zhang
Role: Abby
-
GPU Lead, responsible for ADaS 2.0 GPU integration, deployment and testing
-
Assisting with general debugging in other task areas
-
Organizing GitHub/codebase and file storage
Role: Simone
-
Backend Lead for reinforcement learning and machine learning components
-
Managing delegation of code issues in GitHub and checking progress
-
Coordinating dataset preparation and transformations
Role: Aimee
-
Design, Frontend, and Large Language model (LLM) lead
-
Assisting with general debugging across the project
-
Responsible for unit and system integration testing
-
Organizing GitHub/codebase and file storage
Role: Gloria
-
Developing and implementing LLM code components
-
Assisting with documentation and organization of file storage
Role: Simone
-
Assigning tasks and roles for weekly and overall project progress
-
Communicating concerns/issues and coordinating check-ins with Dr. Watkins (advisor)
We are storing all notes, presentations, and PDF versions of reference literature to this OneDrive Project Folder: