Introduction to AI for Cybersecurity

CIS 400 / CIS 600 / CSE 400 / CSE 691 · Syracuse University · Fall 2026 Tu/Th 5:00–6:20 PM · CST 4-201 · Aug. 25 – Dec. 8, 2026 Instructor: Kristopher Micinski (kkmicins@syr.edu) · Phone 940-399-8924

Office Hours

Office hours are currently by appointment–my office is currently being set up in the new AI institute at Syracuse University, and I am planning to move in during early September. I will announce when I am ready to meet in the office. For now, please meet with me via Zoom or after class. If there are emergent concerns, we can arrange an in-person meeting, please email and we can set it up.

Course description

This course rigorously studies the impact of emerging AI systems on the principles and practices of cybersecurity. Topics include AI-assisted exploit generation and code auditing, autonomous social-engineering attacks, and AI-driven defense strategies such as automated intrusion detection and adaptive threat response. A recurring theme is that most of these vulnerabilities are the same classical failure to separate control from data, and that every offensive capability has a defensive mirror. Additional work is required for graduate students (CIS 600 / CSE 691).

Prerequisites

CIS 351 and CSE 484 (these may also be taken as co-requisites). The CSE 484 requirement may be waived with instructor permission. Comfort with C, a scripting language, and basic systems concepts is assumed. No prior machine-learning background is required.

Audience

Students matriculated in the Computer Science BS, Computer Engineering BS, or AI Science BS. The graduate sections (CIS 600 / CSE 691) are open to MS and PhD students in Computer Science, Computer Engineering, AI Science, and Cybersecurity. Senior undergraduates and MS students are the primary audience. Credits: 3. Course fees/costs: none.

Learning objectives

1. Explain how AI systems can be used to both strengthen and undermine cybersecurity defenses.
2. Analyze the capabilities and limitations of AI-based approaches to vulnerability detection and threat analysis.
3. Evaluate the risks that AI poses to existing security models and practices.
4. Apply AI techniques to solve practical cybersecurity problems.
5. Assess the ethical and policy implications of deploying AI in security contexts.
6. Present findings on AI-cybersecurity topics through written analysis and project-based work.

Undergraduate shared-competency tag: Information Literacy & Technological Agility.

Texts

No required text. The following are optional references:

• Ross Anderson, Security Engineering: A Guide to Building Dependable Distributed Systems, 3rd ed., Wiley, 2020.
• Anthony D. Joseph, Blaine Nelson, Benjamin I. P. Rubinstein & J. D. Tygar, Adversarial Machine Learning, Cambridge University Press, 2019.
• Edward Raff, Inside Deep Learning: Math, Algorithms, Models, Manning, 2022.
• Gareth James et al., An Introduction to Statistical Learning: With Applications in Python, Springer, 2023.

Assigned papers and readings are listed on the schedule and collected on the resources page.

Course requirements and expectations

• Class project. A course project carried out over the last six weeks of the semester, alone or in a group (maximum three per group; higher expectations for larger groups). It is presented during the last two weeks of class. (Graduate projects engage at a higher level, applying concepts from state-of-the-art research.)
• Presentation. Students are divided into groups and assigned a research paper presentation. On the site’s operational schedule these run as short student research presentations that open a marked session most weeks.
• Weekly notes & reflections. Students take detailed notes and write a weekly reflection on the week’s material, graded by the instructor. Due Friday at 11:59 PM (subject to change with notice); the two lowest reflection grades are dropped.
• Homework. Roughly four problem sets, including practice exam questions. Grading is completion-based, and solutions are provided well ahead of the exams. (Graduate homework also includes problems drawn from research papers.)
• Participation. In-class engagement — attending lecture, and discussing readings and papers (including our discussion days and guest lectures) — is graded.
• Exams. Three in-class written exams plus an optional cumulative final. The lowest of these four grades is dropped, so three exams count at 13⅓% each (40% total); a student satisfied with their three exam grades may choose not to sit the final. Exam dates are announced in class and posted on the course site at least two weeks in advance. (Graduate students take a distinct, more theoretical exam.)

Grading

* Graduate projects are expected to engage at a higher level of intellectual merit, applying concepts from state-of-the-art research publications.   ** Graduate homework also includes problems drawn from research papers.   *** Graduate students are given a different exam with a higher bar for theoretical knowledge.

Grade scale (CIS 400 / CSE 400). A 93.0–100 · A− 90.0–92.9 · B+ 87.0–89.9 · B 83.0–86.9 · B− 80.0–82.9 · C+ 75.0–79.9 · C 70.0–74.9 · C− 60.0–69.9 · D 50.0–59.9 · F <50. (Graduate sections CIS 600 / CSE 691 use the same scale but do not award D; the passing floor is F <60.)

Course-specific policies

Course website and communication. Course materials, assignment write-ups, and announcements are posted on the course site. Email (kkmicins@syr.edu) is the official channel for individual questions; please allow up to two business days for a reply, and expect longer response times on weekends.

Late work. Weekly reflections are due Friday at 11:59 PM and are not accepted late, since they are tied to that week’s material; the two lowest reflection grades are dropped to accommodate ordinary conflicts. Projects and problem sets may be submitted up to 48 hours late with a 10% penalty. Extensions beyond this require advance arrangement with the instructor, and accommodations arranged through the Center for Disability Resources or Student Outreach and Support are honored without penalty.

Authorized use of security tools and techniques. This course teaches offensive techniques (binary exploitation, automated exploit generation, adversarial machine learning, prompt injection) for defensive and scholarly purposes. All hands-on work must be performed only against the targets, virtual machines, and infrastructure provided for the course, or against systems you own and are explicitly authorized to test. Using these techniques against Syracuse University systems, other students’ machines, or any third-party system without written authorization is prohibited, may violate the Syracuse University Information Technology Resources Acceptable Use Policy and state and federal law, and will be referred for disciplinary action.

Relationship to CSE 643. Buffer overflows and related memory-safety attacks are also covered in CSE 643 (Computer Security). The treatment in the two courses is complementary: CSE 643 approaches the topic through the SEED Labs hands-on exercises, while this course focuses on AI-assisted discovery and exploitation of such vulnerabilities. Students may take both courses.

Attendance and electronics. Attendance is expected (see the University Attendance Policy) and participation is graded. Laptops and tablets are welcome for coursework; please keep them to course-related use during lecture and discussion.

Use of AI

Students. AI is permitted on the course project and homework (with attribution). See each assignment’s instructions for which tools are permitted, to what extent, and the citation requirements. If no instructions are provided for a specific assignment, no use of any AI tool is permitted. Any AI use beyond what a course assignment details is explicitly prohibited except when documented permission is granted.

Instructor. The instructor has used AI to generate portions of the course material — specifically, AI coding agents to help develop the website and interactive teaching-focused applications, and generative AI to help edit portions of the class slides and notes. In all cases the instructor takes full responsibility for the correctness and relevance of all material used in this class.

University policies and services

Syracuse University policies and services on attendance, religious observances, Orange Success 2.0 progress reports, student mental health, disability-related accommodations (CDR), academic integrity, the student academic work policy, discrimination and Title IX, and email as official communication all apply to this course and are reproduced in full in the official PDF syllabus. See also the Syracuse University Policies site and the Center for Disability Resources (disabilityresources.syr.edu) — contact CDR as early as possible, since accommodations are generally not applied retroactively.