I am PhD candidate at the Department of Electrical Engineering and Computer Science (EECS) at University of Tennessee, Knoxville, advised by Dr. Jian Liu. My research focuses on AI security, federated learning, and generative models, with a particular interest in privacy-preserving and trustworthy machine learning systems and smart healthcare. My research work has been published at top-tier mobile-computing/AI/security/bio-medical venues (e.g., IEEE S&P/Oakland, ACM AsiaCCS, ACM IJCAI, ACM UbiComp, and IEEE EMBC)
Research Interest
Robust and Trustworthy AI
- Federated Learning
- Differential Privacy
- Machine Unlearning
- Algorithmic Fairness
Responsible Content Governance
- Creative Content Protection
- Generative Model Auditing
- Watermarking
- Foundation Model Security
Smart Healthcare and Fitness
- Intelligent Fitness Technologies
- Multimodal Sensing
- Passive Health Tracking
- Early Disease Detection
Publications
Bauder, C., Wu, T., Meerza, S.I.A., Fathy, A., Liu, J. “mm-RunAssist: mmWave-based Respiratory and Running Rhythm Analysis During Treadmill Workouts.” Accepted at ACM IMWUT/UbiComp, Espoo, Finland, Oct 2025.
Wu, T., Wu, Y., Poudel, B., Meerza, S.I.A., et al. “VibRun: Real-time Unobtrusive Gait Analysis for Treadmill Running via Footstep Vibrations.” Accepted at ACM IMWUT/UbiComp, Espoo, Finland, Oct 2025.
Meerza, S.I.A., Liu, L., Zhang, J., Liu, J. “GLocalFair: Jointly Improving Global and Local Group Fairness in Federated Learning.” AAAI PPAI, Philadelphia, USA, Feb 2025.
Meerza, S.I.A., Sun, L., Liu, J. “HarmonyCloak: Making Music Audio Unlearnable for Generative AI.” IEEE S&P (Oakland), San Francisco, USA, May 2025. (Acceptance Rate: 14%)
Meerza, S.I.A., Liu, J. “EAB-FL: Exacerbating Algorithmic Bias Through Model Poisoning Attacks in Federated Learning.” IJCAI, Jeju, South Korea, Aug 2024. (Acceptance Rate: 14%)
Meerza, S.I.A., Sadovnik, A., Liu, J. “ConFUSE: Confusion-based Federated Unlearning with Salience Exploration.” IEEE ISVLSI, Knoxville, USA, July 2024.
Cui, Y., Meerza, S.I.A., et al. “RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense.” ACM AsiaCCS, Melbourne, Australia, July 2022. (Acceptance Rate: 16%)
Ahamed, A., Meerza, S.I.A. “Iris Recognition using Curvelet Transform and Accuracy Maximization by Particle Swarm Optimization.” IEEE WNYISPW, New York, USA, Nov 2022.
Meerza, S.I.A., et al. “Fair and Privacy-Preserving Alzheimer's Disease Diagnosis Based on Spontaneous Speech Analysis via Federated Learning.” IEEE EMBC, Glasgow, Scotland, July 2022.
Meerza, S.I.A., et al. “Precise Warfarin Management through Personalized Modeling and Control with Limited Clinical Data.” IEEE EMBC, Guadalajara, Mexico, Nov 2021.
Meerza, S.I.A., Ahmed, A. “Food Insecurity Through Machine Learning Lens: Identifying Vulnerable Households.” AAEA & WAEA Joint Meeting, Austin, Texas, Aug 2021.
Meerza, S.I.A., et al. “Q-Learning Based Particle Swarm Optimization Algorithm for Optimal Path Planning of Swarm of Mobile Robots.” IEEE ICASERT, Dhaka, Bangladesh, May 2019.
Meerza, S.I.A., et al. “Performance Evaluation of Different Algorithms for Handwritten Isolated Bangla Character Recognition.” IEEE ICREST, Dhaka, Bangladesh, Jan 2019.
Meerza, S.I.A., et al. “Optimal Path Planning Algorithm for Swarm of Robots Using Particle Swarm Optimization Technique.” IEEE ICITISEE, Yogyakarta, Indonesia, Nov 2018.
Media Mentions & Highlights
The Art of Poison-Pilling Music
Benn Jordan explores our HarmonyCloak method on YouTube.
Watch Video →
Pitch Perfect Protection
Featured on TorchBearer Magazine for protecting music from generative AI using HarmonyCloak.
Read More →
How to Poison AI Music Scrapers
Appeared on Kaleidoscope’s Apple Podcast discussing our poisoning method for AI.
Listen Now →.webp)
Protect Me!
Appeared on The Illiac Suite - Music and AI’s Apple Podcast discussing our HarmonyCloak method.
Listen Now →- Jul. 2025 how to poison AI music scrapers — killswitch@kaleidoscope (Apple Podcast)
- May. 2025 Pitch perfect protection. EurekAlert
- Apr. 2025 The Art Of Poison-Pilling Music Files. Benn Jordan (YouTube) (615k Views)
- Dec. 2024 You can’t hear it, but University of Tennessee tool 'cloaks' songs to protect music from AI Knox News
- Dec. 2024 New AI tool HarmonyCloak shields musicians’ work from AI copying The AI Musicpreneur
- Oct. 2024 New tool makes songs unlearnable to generative AI Microsoft Network
- Oct. 2024 Bonne nouvelle pour les droits des artistes: HarmonyCloak empoisonne les IA pour protéger la musique! FURTURA
- Oct. 2024 HarmonyCloak slips silent poison into music to corrupt AI copies New Atlas
- Oct. 2024 New tool makes songs unlearnable to generative AI TechXplore
- Oct. 2024 Someone has come up with a cloaking device to fight bogus AI music. It’s pretty cool Alan Cross’ A Journal of Musical Things
- Oct. 2024 HarmonyCloak: A New Tool to Protect Musicians from AI Copyright Infringement The Outpost
- Oct. 2024 HarmonyCloak: Innovative AI Solution to Safeguard Music from Unauthorized Scraping by Generative AI Platforms Ainvergo
- Oct. 2024 Herramienta dificulta a la IA entrenarse con canciones Tecnología
- Oct. 2024 New tech makes songs invisible to AI, protecting artists from copycats Knowledge
- Oct. 2024 Protéger sa musique des IA, c’est possible! NDD.news
- Oct. 2024 Liu’s New Tool Makes Songs Unlearnable to Generative AI UTK News
- Oct. 2024 This app is saving musicians by poisoning the AI so it stops stealing music Softonic
- Oct. 2024 HarmonyCloak: The Silent Savior Against AI Music Theft ProjectREYLO
- Oct. 2024 HarmonyCloak: Protección musical contra La Ia Generativa WWWHATSNEWS
- Oct. 2024 Musique: les artistes vont pouvoir ‘empoisonner’ leurs œuvres pour que les algorithmes ne puissent plus s’en inspirer Francetvinfo
- Oct. 2024 Harmony Unleashed: AI’s Musical Revolution Silenced Mischa Dohler
Latest News
- [July 2025] Our paper "VibRun: Real-time Unobtrusive Gait Analysis for Treadmill Running via Footstep Vibrations" has been accepted to ACM IMWUT/UbiComp'25! Congratulations to our lead student, Tianhao!
- [July 2025] Our paper "mm-RunAssist: mmWave-based Respiratory and Running Rhythm Analysis During Treadmill Workouts" has been accepted to ACM IMWUT/UbiComp'25! Congratulations to our lead students, Chandler and Tianhao!
- [March 2025] I have been awarded Gonzalez Family 2025 Outstanding Graduate Research Assistant Award!
- [January 2025] Our paper "GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learning" has been accepted to The 6th AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-2025)!
- [September 2024] Our paper "HarmonyCloak: Making Music Unlearnable for Generative AI" has been accepted to IEEE S&P/Oakland 2025!
Awards & Grants
Awards
- Gonzalez Family Outstanding Graduate Research Assistant, UTK EECS, 2025 — For outstanding performance as a research assistant.
- Honorable Mention (Team), MagNet Challenge, Princeton University, NJ, 2023.
- Chancellor’s Award and Vice‑Chancellor’s Award, AIUB Convocation, 2020 — For academic distinction and master’s research.
- Winner (Team), Digital Innovation Fair (Khulna Division), ICT Division, Government of Bangladesh, 2015.
- Top 20 Nomination, Young Bangla Youth Award, ICT Division, Bangladesh, 2015.
- 1st Runner‑up (Team), Project Showcasing, Esonance, IUT, Dhaka, 2014.
Grants
- NSF INTERN Supplement, $55,000 — Non‑Academic Research Internship for Graduate Students, 2024.
- EERE Fellow, $10,000 — U.S. Department of Energy & UTK, 2022‑2023.
- Tennessee’s Top 100 Fellow, $40,000 — University of Tennessee, 2021‑2025.
- Merit Scholarship, Khulna University of Engineering and Technology, 2012‑2015.