Fall 2026 · CS 562 · Section SML
Hands-on Agent Security Labs
Course logistics
What you will learn
- Propose and develop security solutions that use generative AI.
- Explain the technical and social dimensions of security and privacy in AI systems.
- Analyze research on threats to machine learning systems and approaches to protecting them.
- Evaluate the effectiveness and limitations of security and privacy defenses.
Hands-on labs
Eleven hands-on security labs, including Capture-the-Flag (CTF) challenges, progress from single-agent tool use to adaptive reasoning, multi-agent coordination, and long-horizon problem solving.
Team research project
Teams of two or three investigate a problem at the intersection of machine learning, security, and privacy. Milestones include a midterm report and lightning talk, followed by a final report and poster presentation.
Milestones & assessment
- October 14 & 16: Midterm project presentations. The midterm report and presentation account for 20% of the final course grade.
- December 9: Final poster presentation. The final report and presentation account for 25% of the final course grade.
Poster preparation
Submit a poster PDF through the Siebel poster printing service at least 48 hours in advance. Arrive 15 minutes early for setup and keep posters on display throughout the session.
Assessment
- Hands-on Labs (40%): There will be 11 hands-on labs during the semester. Your lowest lab grade will be dropped. The remaining 10 lab grades will count equally toward the lab portion of your final grade.
- Team Project (45%): midterm report/presentation (20%), final report/presentation (25%)
- Participation (15%): Participation includes active engagement during class discussions, collaborative activities, and the team project poster session.
Generative AI Use Policy
This course distinguishes between AI systems studied and built in course activities and AI tools used to assist with coursework.
AI as part of the assignment: Labs and projects may require students to configure, build, run, and evaluate LLM-based agents. These activities are part of the course's technical content. Follow the assignment instructions for model access, permitted tools, and evaluation requirements. Document the models, tools, and configurations used so that your results can be understood and reproduced.
Optional AI assistance: Using GenAI to help brainstorm, explain concepts, debug code, or improve writing is permitted but not required, unless an assignment specifies otherwise. Disclose this assistance in an AI Use Statement. You remain responsible for the correctness, originality, and explanation of your submitted work.
Access and costs: Students are not expected to purchase personal subscriptions to commercial AI tools, and the course does not reimburse such subscriptions. Grades will not depend on access to paid AI features. If you cannot access a model or tool required for an assignment, contact the instructional team before incurring any costs.
For university guidance on available tools and responsible use, see Illinois AI applications and Grainger generative AI resources.
Important Note about Appropriate Use of AI
AI programs are not a replacement for critical thinking, analysis, creativity, originality, or problem-solving. Engineering is a craft that develops through practice, experience, and the gradual development of technical skills and intuition.
GenAI tools may be used to support your learning and engineering work. Appropriate uses may include brainstorming, explaining unfamiliar concepts, exploring design alternatives, debugging, improving clarity, or identifying possible approaches to a problem.
However, you remain responsible for the work you submit. You should be able to explain and defend your design decisions, calculations, code, analysis, and conclusions without relying on an AI system.
You are also responsible for verifying AI-generated information. GenAI tools can produce incorrect calculations, fabricated information or references, inappropriate or insecure code, and explanations that sound convincing but are incorrect. You are expected to review, evaluate, and verify AI-generated suggestions rather than accepting them uncritically.
How to Disclose AI Use
If you use GenAI assistance with your coursework, include a brief AI Use Statement with your submission. The statement should identify: the AI tool you used; what you used it for; and how the AI-generated output influenced your final work.
For example:
AI Use Statement: I used ChatGPT to help identify possible causes of an error in my Python code. I provided the error message and asked for debugging strategies. One suggestion helped me locate an indexing error. I corrected and tested the code myself, and I independently completed the analysis and conclusions.
AI Use Statement: I used Microsoft Copilot to suggest improvements to the grammar and clarity of my lab report. The technical content, calculations, figures, and conclusions are my own.
AI Use Statement: I used ChatGPT to brainstorm several possible concepts for the preliminary design. I evaluated the suggestions independently and developed the final design myself.
If you did not use optional GenAI assistance, no AI Use Statement is required. You must still document the AI models and tools used as part of the assigned lab or project.
When you are uncertain whether a particular use of GenAI is appropriate, ask the instructional team before submitting the work.
Academic Integrity Policy
Students must follow the university's guidelines on academic conduct. This course will have a zero-tolerance policy regarding plagiarism. You (or your team) should complete all the labs and project tasks on your own. When you use the code or tools developed by other people, please acknowledge the source. If an idea or a concept used in your project has been proposed by others, please make the proper citations. All electronic work submitted for this course will be archived and subjected to automatic plagiarism detection. Whenever in doubt, please seek clarifications from the instructor. Students who violate Academic Integrity policies will be immediately reported to the department and the college.
Accommodations
To obtain disability-related academic adjustments and/or auxiliary aids, students with disabilities must contact the course instructor and the Disability Resources and Educational Services (DRES) as soon as possible. To contact DRES, you may visit 1207 S. Oak St., Champaign, call 217-333-1970, e-mail disability@illinois.edu, or go to the DRES website at go.illinois.edu/DRES. If you are concerned you have a disability-related condition that is impacting your academic progress, there are academic screening appointments available on campus that can help diagnosis a previously undiagnosed disability by visiting the DRES website and selecting “Sign-Up for an Academic Screening” at the bottom of the page.