Saeid Tizpaz-Niari joins CS faculty
Saeid Tizpaz-Niari joins CS faculty Heading link
Assistant Professor Saeid Tizpaz-Niari (سعید تیزپاز نیاری) joined the computer science department on January 1. His research is at the intersection of software engineering, AI fairness, and cybersecurity.
Most recently, Tizpaz-Niari worked as an assistant professor at the University of Texas at El Paso. He received his PhD in computer engineering from the University of Colorado at Boulder, his MS in information technology from the Sharif University of Technology in Tehran, Iran, and his BS from the University of Tabriz in East Azerbaijan, Iran.
AI has become deeply integrated into modern software development practices. Developers now leverage pre-trained deep neural networks—AI models that emulate human brain processing—and large language models capable of processing and generating human language. While AI-powered software offers significant advantages, it can also introduce novel classes of bugs and vulnerabilities. Because these models derive their logic from historical data, they may potentially introduce fairness bugs.
“If our future software will incorporate these AI solutions, what are the new challenges with respect to their safety, security, and fairness?” Tizpaz-Niari asked. “Some of these issues were not in the traditional software system.”
Traditionally, software systems were directly coded by programmers. In contrast, AI models, particularly large language models, are often opaque “black-box” algorithms where decision logic is implicitly encoded through training data. This opacity makes understanding their inner workings challenging. Consequently, emerging bugs in AI systems frequently require relational analysis, comparing model outputs across different contextual instances or demographic backgrounds.
His shift toward social justice was rooted in his personal experiences when, as an Iranian, he was refused certain job opportunities in the U.S. At UTEP, he continued his focus on fairness, ensuring everyone, regardless of their background, was given similar opportunities solely based on their qualification.
“When I started my faculty job, I established an interesting connection between confidentiality and fairness. With confidentiality, you want to ensure that two inputs that have the same public data receive similar software outcomes, so no secret data influences the outcome,” Tizpaz-Niari said. “With fairness, you have to compare two people who have similar relevant factors, and they should receive the same outcome, even if they have different backgrounds.”
Tizpaz-Niari has two active National Science Foundation (NSF) grants: one from the NSF Security, Privacy, and Trust in Cyberspace program (SaTC) and another from the agency’s Designing Accountable Software System program (DASS). The SaTC project is looking at the meta-functional properties in AI software, issues beyond functional correctness, including availability and confidentiality.
The DASS grant is focused on accountable tax preparation software. He is working to find bugs in open-source tax preparation software that may hinder low-income individuals from receiving all the credits or deductions they are entitled to under tax law.
Tizpaz-Niari has had experience with the Volunteer Income Tax Assistance program (VITA), which is within the Internal Revenue Service (IRS). Low-income individuals can go to various sites and file their taxes for free. But the centers are staffed with volunteers who may not be able to answer all of a taxpayer’s questions. Tizpaz-Niari hopes to use AI to support these volunteers in finding the correct answers for their clients. In particular, his group is working on a recent research paper with the IRS on the topic of AI-assisted tax preparation for VITA and has previously presented papers to the IRS conference in Washington, D.C.
“I volunteered with a VITA site, learn about their issues and how the process works like an anthropologist,” Tizpaz-Niari said. “I am a technical person, and I want to come up with technical solutions, but I collaborate with CS researchers, lawyers, and social scientists to understand the implications of such solutions on humanity, society, and the world. I’m currently collaborating with a psychology professor and a human-computer interaction researcher.”
Tizpaz-Niari was drawn to Chicago and UIC, in particular for its diversity. His previous professorship was also with a Hispanic Serving Institution (HSI). This semester, he is teaching a special topics course, CS594, Responsible AI Engineering.