LSU Computer Science Professor Leading Project to Increase Security in Federated Learning
September 13, 2023
BATON ROUGE, LA – Federated learning is a technique that has gained attention for its potential to improve privacy, security, and efficiency in various sectors. At times, in order to improve the quality and robustness of this technique, it is subject to periods of “critical learning.” However, it is during these periods that outside agents have an opportunity to launch precise and damaging attacks.
In order to better understand these opportunities and attacks, LSU Computer Science Assistant Professor Hao Wang is working with Assistant Professor Jian Li, from the Department of Computer Science at Stony Brook University, and Associate Professor Xu Yuan, from the Department of Computer & Information Sciences at the University of Delaware. Their work is funded by a $500,000 National Science Foundation grant, and its goal is to deliver a prototype federated learning system with algorithms that detect critical learning periods and employ attack/defense methods.
“A critical learning period is an inherent property of the training process of deep-learning models; it could amplify a variety of attacks, including data-poisoning attacks and model-poisoning attacks,” Wang said. “In other words, if these attacks happen during the critical learning periods, they can bring much more damage to the [artificial intelligence] model.
“One example is backdoor attacks, which involve embedding a hidden pattern or trigger into the training data, such that the compromised model behaves normally for most inputs but produces incorrect or malicious output when the trigger is present. The attacker usually has control over both the trigger and the corresponding malicious output, allowing them to exploit the model for specific tasks without being easily detected.”
Some examples of the way federated learning is utilized in various industries are:
- Fraud detection in fintech, or financial technology – Banks and financial institutions use federated learning to build more robust fraud detection models by learning from a wide array of decentralized data points without compromising user privacy.
- Disease prediction and prevention in healthcare – Medical institutions use federated learning to collaborate and predict disease outbreaks or patient outcomes without sharing sensitive patient data.
- Autonomous vehicles – Car manufacturers use federated learning to improve the safety and efficiency of autonomous driving algorithms without sharing sensitive data belonging to drivers.
As Wang and his team’s research progresses, they will share datasets, models, algorithms, etc., with the AI and security community. This will allow their peer researchers to reproduce their experiments and gain insight into their work. Additionally, the team will involve students at the K-12, undergraduate, and graduate levels in their research.
“For undergraduate students, we plan to attract and involve them by providing research assistant positions and hosting robust AI workshops and hackathons,” Wang said. “Two students—Michelle Vo and Sejal Patel—joined my lab from LSU Women in Computer Science and worked on backdoor attacks to AI models. I am also discussing with the Society for Asian Scientists and Engineers about hosting a robust AI hackathon for undergraduates. We plan to release toolkits to participants to observe and exploit the critical learning periods of AI models.
“We will also involve K-12 students in our project. A few observations and discoveries from the project will be packaged into hands-on projects for students to explore AI and security.”
Like us on Facebook (@lsuengineering) or follow us on Twitter and Instagram (@lsuengineering).
###
Contact: Joshua Duplechain
Director of Communications
225-578-5706
josh@lsu.edu
Latest College of Engineering News
- LSU Computer Science Student Builds Interactive Lobby ExperienceMay 10, 2024BATON ROUGE, La. – The lobbies of LSU's Music & Dramatic Arts Building, School of Music Building, and Tiger Band Hall will soon feature a helpful new interactive digital kiosk experience for students and patrons alike, built by LSU College of Engineering undergraduate student Caleb Langley.
- LSU Electrical, Computer Engineering Seniors Design Virtual Lab for Remote ExperimentsMay 13, 2024BATON ROUGE, LA - As part of their senior capstone project, four LSU Electrical and Computer Engineering seniors designed a virtual lab that will allow LSU Mechanical Engineering students to conduct pipe-flow experiments from a remote location. The project's sponsor, LSU Mechanical and Industrial Engineering Department Chair and Professor Dimitris Nikitopoulos, thought of the project when students were stuck at home during the pandemic. The group's efforts are funded by Chevron.
- Mechanical Engineering Seniors Design Equipment for B-52s at Barksdale AFBMay 10, 2024BATON ROUGE, LA - As part of their senior capstone project, six LSU Mechanical Engineering seniors have been working with Barksdale Airforce Base in Bossier City, La., to design an apparatus that will enable airmen to more easily work on or change out the engines on their B-52 bombers. Considering Barksdale AFB houses 26 B-52s, and each B-52 has eight engines, the students' design should definitely come in handy.
- College of Engineering Honors Five at Evening of Engineering Excellence EventMay 8, 2024BATON ROUGE, LA - The LSU College of Engineering recently held its first Evening of Engineering Excellence event on April 25, inducting several new members into its Society for Engineering Excellence and Hall of Distinction.
- LSU Mechanical Engineering Instructor Creates ASPIRE Course for EducatorsMay 7, 2024BATON ROUGE, LA - Look! Up in the sky! It's a bird! It's a plane! It's...a drone. Drones are literally taking off and LSU Mechanical Engineering Senior Instructor Andrew Becnel wants students to keep up. Becnel, who is a graduate of LSU's Mechanical Engineering program and has a master's degree and Ph.D. in aerospace engineering from the University of Maryland, understands the importance of drone technology, especially in Louisiana.
- LSU Research Team Working to Increase Supply of Affordable, Resilient Housing in High-Risk AreasMay 6, 2024BATON ROUGE, LA - With hurricane season around the corner, a team of LSU researchers is exploring the feasibility of FORTIFIED® elevated manufactured homes as a solution for lower- and middle-income residents in high-risk areas. The outcomes of the project have the potential to enhance housing supply significantly, particularly in areas prone to natural disasters, offer greater safety to residents, and reduce burden on the National Flood Insurance Program and other disaster prevention, mitigation, and relief endeavors.