Students are encouraged to form a group of three to implement both the midterm and final projects.

Midterm Project

  • Objective: Build an AI application such as object detection, voice conversion, or large language model agent to solve a specific problem or improve existing solutions in an innovative way.

  • Functionality: Have a functional API or user interface to demonstrate its capabilities. It should be user-friendly and effectively showcase the role of AI in solving the problem.

  • Documentation: Include a README file with clear instructions on how to run your application.

  • Format: Submit your code repository via [GitHub or Canvas] and ensure all files are properly organized and documented.

Projects will be graded based on technical contribution, functionality, user experience, and documentation. We encourage you to think creatively and explore diverse applications of AI. Whether it is enhancing healthcare, optimizing supply chains, or developing new entertainment technologies, the possibilities are endless!

Final Project

  • Objective: Evaluate the AI application that you have built in the midterm project based on one specific aspect of trustworthiness:
    • Privacy
    • Fairness and Bias
    • Safety and Security
    • Reliability and Robustness
    • Transparency and Explainability
    • Accountability and Responsibility

  • Functionality: You need to write code to evaluate and analyze its performance against the trustworthiness criteria discussed in the course. For example, you can design different attacks to evaluate the potential security and privacy risks in your built AI applications. You can also do benchmark tests on your AI systems to assess the fairness and bias issues in your AI application.

  • Documentation: Include a README file with clear instructions on how to run your application.

  • Format: Submit your code repository via [GitHub or Canvas] and ensure all files are properly organized and documented.

Projects will be graded based on technical contribution, functionality, user experience, and documentation. We encourage you to read research papers, industry reports, and ethical guidelines on AI trustworthiness. Just think critically and creatively about the role of trustworthiness in AI applications.

Presentation and Essay

  • Midterm Presentation: Describe your midterm project, highlighting the objective, related work, challenges, solutions, and your evaluation progress.

  • Final Presentation: Describe your final project, including the motivation, related work, challenges, solutions, and evaluation progress. You may also want to discuss how your final project built upon or differed from your midterm project.

  • Essay: Each group will submit ONE project essay in at least 6 content pages (excluding references) following the format in NeurIPS 2024. The content of the essay should include both the midterm and final projects. The essay should follow the general structure of a research paper:

    • Introduction
    • Related Work
    • System Design
    • Evaluation
    • Conclusion
    • Acknowledgment: Each group member should explain the individual contribution to both the midterm and final projects.