This seminar-based course explores state-of-the-art research in the domains of security, privacy, and data analytics, with a focus on both traditional machine learning and emerging Generative AI (Gen AI) models. It discusses how these models can be both tools and targets in security scenarios, addressing the security and privacy concerns associated with machine learning and big data, as well as their roles in decision-making for security and privacy. The course also delves into critical overlapping concepts such as information integrity, trust, fairness and bias, providing a holistic view of the challenges and solutions in the intersection of AI, security, and privacy. Through real-world case studies and practical examples, students will contextualize these theoretical concepts and understand their applications. Students will engage in interactive discussions, presentations, and collaborative projects, fostering a dynamic learning environment. By the end of the course, students will be equipped to critically analyze research papers, grasp the latest trends in AI security, and develop strategies to mitigate risks, preparing them to contribute to advancements in this rapidly evolving field.
A bachelor's degree in Computer Science or a related field is required. While no prior experience in security and privacy is necessary, students must be willing to seek out and read background material as needed. A basic understanding of deep learning and general machine learning concepts is expected. Students enrolling in the course should be highly motivated, ready to work hard, and prepared to address any prerequisite gaps they may have.
No required textbook. All course readings will be scientific papers. Each week the instructor lists these papers for students to read before the class.
This is a discussion-based graduate seminar course. Students are expected to attend all class meetings and participate actively in the discussion. Students must inform the instructor if they cannot attend a class due to a conference or other major personal or professional obligation.
We will read and discuss 2 papers every week. All students must complete the assigned reading before class to participate fully in class discussions. To facilitate productive class discussions, students must submit a review of each assigned paper to Canvas on Fridays by 11:59 am. Reviews should consist of three brief paragraphs in students’own words (The use of GenAI is strictly prohibited) with the following structure:
Paragraph 1:
Explain the problem and motivation.
Explain the main ideas and technical contributions of the work.
Compare this work with the main prior work.
Explain the methodologies used for evaluation.
List three key strengths and three key weaknesses of this paper. Focus should be more on approach and evaluation.
Paragraph 3:List any future work that you might consider in this line of research.
All students will be the discussion leader for two paper class discussions: one paper presentation individually and one collaboratively with another student. As the discussion leader, the student must prepare a 30-minute presentation covering the paper's main technical contributions, plus at least ten discussion questions. In total, the presentation and discussion should take about 50 minutes. Before the beginning of class, the student should upload their slides as a PDF to the Canvas folder for that reading assignment.
Students will work on a major project in groups of sizes 2--3. Students should propose their projects. However, if needed, the instructor will suggest some projects. Here is the timeline for the projects:
Thursday, February 6th (11:59 pm): Every student submits a project idea for their project. Explain your idea in one or two paragraphs: state your research questions, motivation, and general approach.
Friday, February 7th : Students have 5 minutes to present their ideas in class. Students will decide about their projects and groups at the end of this day.
From Monday, February 10th, to Wednesday, February. 12th: The Instructor and the TA schedule meetings with each group to discuss and refine their idea.
Thursday, February 13th (11:59 pm): Each group submits a finalized version of their project proposal in 2-3 pages. The proposal should state their research questions; hypotheses (if any); general approach; and evaluation metrics. It should also include a timeline with checkpoints and deliverables at those checkpoints. Describe what you hope to accomplish by the end of the semester.
Every week in class: Each group gives an oral progress report (~5 minutes). Describe your progress, and discuss your plan for the next week. Note that this report will be graded.
Thursday, March 20th (11:59 pm): Groups submit a written progress report. Their written progress report should describe their progress to date relative to their proposed timeline, note any problems they have run into, describe your updated plan for the rest of the semester, and include any preliminary results or technical accomplishments. This written report should also include a draft of the related work section for your final paper. This report should be written in the format of a paper using the templates provided here .
Friday, April 25th: All students give a 15-minute final project presentation + 5-minute Q&A in the class in person.
Monday, May 2nd (11:59 pm): Submit a paper including an abstract, introduction (including research questions), related work, methodology, results, discussion, conclusions, and references.
Students are encouraged to submit their project as a full paper to a conference with an appropriate deadline. A paper submission will likely require additional work after the end of the semester.
| Week | Class Date | Papers | Moderator |
|---|---|---|---|
| 1 | Jan. 17 | Introduction, Planning, and Reviewing Papers |
|
| 2 | Jan. 24 | Phishing and Scam
|
Sayak Saha Roy Nowshin Tabassum |
| 3 | Jan. 31 | Online Safety
|
Saurabh Shrinivas Maydeo Michael Danilson Aliu Akinwale |
| 4 | Feb. 7 | Project ideas
|
|
| 5 | Feb. 14 | Good Practices in Data-driven Security Research
| Nikolaos Ntokos John-Phillip Sims |
| 6 | Feb. 21 | Social Media and cybersecurity
|
Sathvik Kumar Katam Nahin Kumar Dey |
| 7 | Feb. 28 | Online Toxicity
|
Nahin Kumar Dey and Tanusree Das Tithy Biraaj Rout |
| 8 | March 7 | Software Security
| Imran Chichkar Biraaj Rout and Saurabh Shrinivas Maydeo |
| 9 | March 14 | Spring Break | |
| 10 | March 21 | Privacy
|
Tim Ryan John-Phillip Sims and Chris Richardson |
| 11 | March 28 | Machine Learning Privacy
|
Sathvik Kumar Katam and Nowshin Tabassum Sadegh Moosavi |
| 12 | April 4 | DeepFakes
|
Chris Richardson Mohammad Sufyaan Saeed |
| 13 | April 11 | Security and Privacy of Language Models
|
Tanusree Das Tithy Mohammad Sufyaan Saeed and Imran Chichkar |
| 14 | April 18 | GenAI for Cybersecurity
|
Tim Ryan and Michael Danilson Nikolaos Ntokos and Aliu Akinwale |
| 15 | April 25 | Final project presentation | |
Course grades will be based on the following. This class will have no exams. Final project presentations will be held on the last day of class.
The UTA Office of Community Standards articulates the university's stance on academic integrity and scholastic dishonesty. These standards extend to the use of GenAI. Unauthorized or unapproved use of GenAI in academic work falls within the scope of these policies and will be subject to the same disciplinary procedures. As the instructor of this course, I have adopted the following policy on Student use of GenAI:
Paper reviews [Prohibition of GenAI Use] : In this activity, the focus is on the development of independent critical thinking and the mastery of subject-specific content. To ensure that all submitted work accurately reflects personal understanding and original thought, the use of Generative AI (GenAI) tools in completing this assignment is strictly prohibited. This policy supports our commitment to academic integrity and the direct measurement of each student's learning against the course's Student Learning Outcomes (SLOs). Any work found to be generated by AI will be subject to academic review.
Grammar check [Unrestricted Use of GenAI] : Students may use GenAI tools freely to assist in fixing the grammar and flow of their reports. It is expected that students will engage with these tools ethically and responsibly. The students are required to include a statement on what GenAI tools they utilized and how they used them. Use of GenAI without including the statement will be subject to academic review.
Research Projects [Cited Use of GenAI]: This course permits the use of Generative AI (GenAI) as a resource for completing your research projects. However, transparency is crucial, students are required to include a statement on what GenAI tools they utilized and how they used them. This requirement allows for the acknowledgment of the collaborative nature of GenAI in the learning process while enabling the assessment of student learning to remain focused on the achievement of the course’s Student Learning Outcomes (SLOs). Use of GenAI without including the statement will be subject to academic review.
Students can drop 2 summaries, but at most 1 for a given week. Save these for circumstances such as falling ill or interviewing.
Students will be penalized 25% for every day it is late beyond the designated deadline. You must submit satisfactory versions of your project reports within 4 days of the deadline to pass the class. This policy will be used for the proposal, progress report, and final report.
Students may drop or swap (adding and dropping a class concurrently) classes through self-service in MyMav from the beginning of the registration period through the late registration period. After the late registration period, students must see their academic advisor to drop a class or withdraw. Undeclared students must see an advisor in the University Advising Center. Drops can continue through a point two-thirds of the way through the term or session. It is the student's responsibility to officially withdraw if they do not plan to attend after registering. Students will not be automatically dropped for non-attendance. Repayment of certain types of financial aid administered through the University may be required as the result of dropping classes or withdrawing. For more information, contact the Office of Financial Aid and Scholarships (http://wweb.uta.edu/aao/fao/).
UT Arlington is on record as being committed to both the spirit and letter of all federal equal opportunity legislation, including The Americans with Disabilities Act (ADA), The Americans with Disabilities Amendments Act (ADAAA), and Section 504 of the Rehabilitation Act. All instructors at UT Arlington are required by law to provide “reasonable accommodations” to students with disabilities, so as not to discriminate on the basis of disability. Students are responsible for providing the instructor with official notification in the form of a letter certified by the Office for Students with Disabilities (OSD). Only those students who have officially documented a need for an accommodation will have their request honored. Students experiencing a range of conditions (Physical, Learning, Chronic Health, Mental Health, and Sensory) that may cause diminished academic performance or other barriers to learning may seek services and/or accommodations by contacting: The Office for Students with Disabilities, (OSD) http://www.uta.edu/disability/ or calling 817-272-3364. Information regarding diagnostic criteria and policies for obtaining disability-based academic accommodations can be found at www.uta.edu/disability.
www.uta.edu/caps/ or calling 817-272-3671 is also available to all students to help increase their understanding of personal issues, address mental and behavioral health problems and make positive changes in their lives.
The University of Texas at Arlington does not discriminate on the basis of race, color, national origin, religion, age, gender, sexual orientation, disabilities, genetic information, and/or veteran status in its educational programs or activities it operates. For more information, visit uta.edu/eos.
The University of Texas at Arlington (“University”) is committed to maintaining a learning and working environment that is free from discrimination based on sex in accordance with Title IX of the Higher Education Amendments of 1972 (Title IX), which prohibits discrimination on the basis of sex in educational programs or activities; Title VII of the Civil Rights Act of 1964 (Title VII), which prohibits sex discrimination in employment; and the Campus Sexual Violence Elimination Act (SaVE Act). Sexual misconduct is a form of sex discrimination and will not be tolerated. For information regarding Title IX, visit www.uta.edu/titleIX or contact Ms. Michelle Willbanks, Title IX Coordinator at (817) 272-4585 or titleix@uta.edu.
Students enrolled all UT Arlington courses are expected to adhere to the UT Arlington Honor Code:
I pledge, on my honor, to uphold UT Arlington’s tradition of academic integrity, a tradition that values hard work and honest effort in the pursuit of academic excellence.
I promise that I will submit only work that I personally create or contribute to group collaborations, and I will appropriately reference any work from other sources. I will follow the highest standards of integrity and uphold the spirit of the Honor Code.
UT Arlington faculty members may employ the Honor Code in their courses by having students acknowledge the honor code as part of an examination or requiring students to incorporate the honor code into any work submitted. Per UT System Regents’ Rule 50101, §2.2, suspected violations of university’s standards for academic integrity (including the Honor Code) will be referred to the Office of Student Conduct. Violators will be disciplined in accordance with University policy, which may result in the student’s suspension or expulsion from the University. Additional information is available at https://www.uta.edu/conduct/.