# Welcome to SecureAI ## Building Secure, Ethical, and Trustworthy AI Systems SecureAI is a comprehensive, **self-paced** training program on cybersecurity and privacy for AI systems. Across **12 self-study workshops**, you will build the knowledge and skills to develop AI systems that are technically sound, secure, and ethically responsible, entirely on your own schedule. This is an **independent, self-study guide**: every workshop is delivered as recorded expert panels and lab walkthrough videos, paired with readings and hands-on notebooks you run yourself. There are no live sessions to attend, work through it like an online course, at your own pace. --- ## About the Program The SecureAI Workshop Series brings together leading experts in AI security, cybersecurity, and privacy. Each of the 12 workshops combines: - **Recorded Expert Panels** - Industry leaders and academic experts sharing real-world insights, available to watch anytime - **Hands-on Labs** - Practical experience with code, datasets, and real vulnerabilities through Jupyter notebooks and Google Colab - **Technical Depth** - From fundamentals to advanced attack and defense mechanisms - **Ethical Focus** - Understanding AI risks, bias, fairness, and responsible development - **Learn at Your Own Pace** - No schedules, no attendance, revisit any workshop as often as you like ### How the Program Works - **Format:** Fully self-study and self-paced - **Structure:** 12 workshops, designed to be followed in order over roughly 12 weeks (or any pace you choose) - **Each workshop includes:** a recorded panel/lecture to watch, a written guide to read, and a hands-on lab notebook to run - **Lab Access:** Jupyter notebooks included in this repository, each with a matching Google Colab link - **What you need:** Python and Jupyter (locally), or just a browser with Google Colab --- ## Program Leadership

Mohammed Abuhamad

Program Co-Director & Assistant Professor

Mohammed is an assistant professor of Computer Science with Ph.D. degrees from UCF and INHA University. His research focuses on AI/Deep Learning-based Information Security, Software and Mobile/IoT Security, Adversarial Machine Learning, and AI-based applications. Published in top-tier conferences including ACM CCS, PoPETS, IEEE ICDCS, and IEEE IoT-J.

mabuhamad@luc.edu | Loyola University Chicago

Eric Chan-Tin

Program Director & Associate Professor

Eric is an associate professor in the Department of Computer Science, Director of the Center for Cybersecurity, and PI for the NSA/DHS Center of Academic Excellence in Cyber Defense. His research areas include network security, distributed systems, privacy, and anonymity with 30+ peer-reviewed publications at top venues like ACM CCS, NDSS, and IEEE TIFS.

dchantin@luc.edu | Loyola University Chicago

Loretta Stalans

Program Evaluator

Loretta is the program evaluator ensuring quality delivery and participant success. She manages program assessment, feedback collection, and continuous improvement efforts across the program.

Lstalan@luc.edu | Loyola University Chicago

Maddie Juarez

Administrative Coordinator

Maddie is the administrative coordinator for the SecureAI program, supporting program logistics, coordination, and operations across the workshop series.

mjuarez4@luc.edu | Loyola University Chicago

Mujtaba Nazari

Lab Assistant & Graduate Researcher

Mujtaba is a graduate researcher who maintains the workshop notebooks, datasets, and lab materials. For technical questions about the lab activities or notebooks, please reach out.

mnazari@luc.edu | Loyola University Chicago

--- ## What You'll Learn ### Core Topics Covered #### Security Fundamentals - Threat models in AI systems - Adversarial attacks and defenses - Robustness evaluation and certification - Attack transferability and effectiveness #### Privacy & Federated Learning - Differential privacy concepts - Federated learning protocols - Privacy attacks (membership inference, model inversion) - Privacy-utility tradeoffs #### Ethics & Fairness - Bias detection and mitigation - Fairness metrics and definitions - Algorithmic discrimination - Ethical AI development practices #### Transparency & Explainability - Explainability techniques (LIME, SHAP) - Model interpretability methods - Attacks on interpretability - Trust in AI systems #### Development & Operations - DevOps and MLOps integration - Secure coding practices - Model deployment security - Continuous monitoring #### Governance & Compliance - GDPR and data privacy regulations - CCPA and regional laws - EU AI Act frameworks - Data governance principles - Responsible AI assessment #### Real-World Case Studies - Federated learning attacks - Backdoor attacks in practice - Industry AI security implementations - Best practices from leading organizations --- ## Workshops Overview | # | Title | Includes | | ---- | ------------------------------------------------------------ | ----------- | | **1** | [Introduction and Fundamentals in AI](Workshop01/Introduction_and_Fundamentals_in_AI.md) | Panel Discussion | | **2** | [AI and Threat Models](Workshop02/AI_and_Threat_Models.md) | Lecture + Lab | | **3** | [Adversarial Attacks: White-Box Attacks](Workshop03/Adversarial_Attacks_-_White-Box_Attacks.md) | Lecture + Lab | | **4** | [Adversarial Attacks: Black-Box Attacks](Workshop04/Adversarial_Attacks_-_Black-Box_Attacks.md) | Lecture + Lab | | **5** | [Robustness and Resilience](Workshop05/Robustness_and_Resilience.md) | Lecture + Lab | | **6** | [AI and Privacy: Differential Privacy & Federated Learning](Workshop06/AI_and_Privacy_Differential_Privacy_and_Federated_Learning.md) | Lecture + Lab | | **7** | [Ethics in AI: Bias and Fairness](Workshop07/Ethics_in_AI_-_Bias_and_Fairness.md) | Lecture + Lab | | **8** | [Trust in AI: Transparency, Explainability & Interpretability](Workshop08/Trust_in_AI_Transparency_Explainability_and_Interpretability.md) | Lecture + Lab | | **9** | [AI Development and Security](Workshop09/AI_Development_and_Security.md) | Lecture | | **10** | [AI and Data Governance: Regulations and Standards](Workshop10/AI_and_Data_Govern_Regulations_and_Standards.md) | Panel | | **11** | [Secure Deployment and Operation of AI Systems](Workshop11/Secure_Deployment_and_Operation_of_AI_Systems.md) | Lecture | | **12** | [Case Studies & Real-World Applications: AIShield](Workshop12/Case_Studies_RealWorld_Applications_AIShield.md) | Case Study | --- ## Completing the Program Work through all 12 workshops, watching the sessions and completing the hands-on lab activities, to build knowledge and applied skills at the intersection of AI, cybersecurity, and privacy. **Expected Outcomes:** - Increased knowledge of security, privacy, and ethical aspects of AI systems - Enhanced ability to strengthen cybersecurity measures in your organization - Practical skills to identify vulnerabilities and implement defenses - Understanding of best practices for responsible AI development --- ## Workshop Videos Each workshop's expert panel/lecture and its lab walkthrough are published as videos you can watch on demand. Links are added below as each recording is posted. | Workshop | Speaker | Video | | ----------- | ------------------- | ----------- | | Workshop 1 | Guest Panelists | [Watch](https://drive.google.com/file/d/1MvJCiTjjzkvz_jDT5kYpIYYtqZQUQRIs/view) | | Workshop 2 | Mohammed Abuhamad | [Watch](https://drive.google.com/file/d/13OrSjFWGSHTz-JWLtLj_8Rn_6dW0GlxT/view) | | Workshop 3 | Blaine Hoak | [Watch](https://drive.google.com/file/d/1HLGraovO1Jbh53GfzInjzM9Ryst_tIB4/view) | | Workshop 4 | Blaine Hoak | | | Workshop 5 | Ryan Sheatsley | [Watch](https://drive.google.com/file/d/1sWqyURz6CTu_lHssKfIaPi5wHS1rW5d_/view) | | Workshop 6 | Kai Yue | [Watch](https://drive.google.com/file/d/1fgUae050C8cS5w34WjfWdSXO_s05V1O5/view) | | Workshop 7 | Tamer Abuhmed | [Watch](https://drive.google.com/file/d/1EGLr4cecvcNmd-vrHyORU2JrV_JaLijx/view) | | Workshop 8 | Eldor Abdukhamidov | [Watch](https://drive.google.com/file/d/1ctZygmHqtZcJU2I1BocIu9q5xeSDAjU4/view) | | Workshop 9 | Jaron Mink | [Watch](https://drive.google.com/file/d/1etkx9CoaaCgl1DnSpX_UrYd54DjYshIF/view) | | Workshop 10 | Panel Discussion | | | Workshop 11 | Neophytos Christou | [Watch](https://drive.google.com/file/d/14np7uF0nNehRHdXGtKtpLBZa_9b6ju95/view) | | Workshop 12 | AIShield Case Study | | --- ## Quick Links ### Learning Materials - [View Program Overview](overview.md) - [Workshop 1: Introduction and Fundamentals](Workshop01/Introduction_and_Fundamentals_in_AI.md) - [Workshop 2: AI and Threat Models](Workshop02/AI_and_Threat_Models.md) - [Workshop 3: White-Box Attacks](Workshop03/Adversarial_Attacks_-_White-Box_Attacks.md) - [Workshop 4: Black-Box Attacks](Workshop04/Adversarial_Attacks_-_Black-Box_Attacks.md) - [Workshop 5: Robustness and Resilience](Workshop05/Robustness_and_Resilience.md) - [Workshop 6: Differential Privacy & Federated Learning](Workshop06/AI_and_Privacy_Differential_Privacy_and_Federated_Learning.md) - [Workshop 7: Bias and Fairness](Workshop07/Ethics_in_AI_-_Bias_and_Fairness.md) - [Workshop 8: Transparency, Explainability & Interpretability](Workshop08/Trust_in_AI_Transparency_Explainability_and_Interpretability.md) - [Workshop 9: AI Development and Security](Workshop09/AI_Development_and_Security.md) - [Workshop 10: Data Governance](Workshop10/AI_and_Data_Govern_Regulations_and_Standards.md) - [Workshop 11: Secure Deployment](Workshop11/Secure_Deployment_and_Operation_of_AI_Systems.md) - [Workshop 12: Case Studies & Real-World Applications](Workshop12/Case_Studies_RealWorld_Applications_AIShield.md) - [Resource Library](resources.md) ### Questions & Support - Lab & Notebook Questions: [mnazari@luc.edu](mailto:mnazari@luc.edu) - Program Inquiries: [dchantin@luc.edu](mailto:dchantin@luc.edu) ### External Resources - [Loyola University Chicago](https://www.luc.edu) - [Computer Science Department](https://www.luc.edu/cs) - [Cybersecurity Center](https://www.luc.edu/cybersecurity) --- ## Program Sponsors The SecureAI program is supported by and partners with leading organizations committed to advancing AI security:

--- ## Getting Started ### Before Workshop 1 1. **Set Up Your Environment** - Install Python 3.8+ and Jupyter locally, or plan to use Google Colab (no installation needed) for the labs 2. **Review Prerequisites** - Familiarity with Python, machine learning basics, and command-line tools 3. **Explore Resources** - Browse the [Resource Library](resources.md) for background materials 4. **Start Learning** - Begin with [Workshop 1: Introduction and Fundamentals](Workshop01/Introduction_and_Fundamentals_in_AI.md) ### Running the Labs Each workshop's lab is a Jupyter notebook stored directly in its `WorkshopNN/` directory. On the workshop page you will find two links for each activity: 1. A link to the **notebook file** in this repository 2. A **Google Colab** link to run it in your browser To run a lab on Colab, open the Colab link and save your own copy to your Google Drive (**File → Save a copy in Drive**); you can then run it with your own credentials and save your results at the end. --- ## Frequently Asked Questions **Q: Do I need to know advanced AI/ML concepts?** > While basic familiarity with Python and machine learning is helpful, we cover the necessary foundations. Review our [prerequisite materials](resources.md) if you're new to ML. **Q: Can I go at my own pace?** > Yes, the entire program is self-study. Work through the 12 workshops in any order or timeframe that suits you, though we recommend following them in sequence since later workshops build on earlier ones. **Q: Do I need to install anything to run the labs?** > No. Every lab notebook has a Google Colab link so you can run it in your browser with no local setup. If you prefer, you can also run the notebooks locally with Python and Jupyter. **Q: How much time should I plan per workshop?** > Plan for approximately 4-5 hours per workshop: time to watch the session and work through the hands-on lab. --- ## Explore the Program Ready to dive in? Start with any of these sections: - [Program Overview & Learning Paths](overview.md) - Understand the complete curriculum - [Workshop 1: Introduction & Fundamentals](Workshop01/Introduction_and_Fundamentals_in_AI.md) - Begin with foundational concepts - [Resource Library](resources.md) - Access papers, tools, datasets, and external materials --- **Welcome to SecureAI! Let's build a more secure AI future together.**