Shimaa Ahmed

Staff Research Scientist

Team: Identity and machine learning security

Research areas: Privacy and Security, Responsible AI

Shimaa Ahmed joined Visa Research as a Staff Research Scientist in March 2024. Shimaa received her Ph.D. in Computer Engineering from the University of Wisconsin-Madison in January 2024. Her Ph.D. thesis was on trustworthy user-machine interactions. Her research was focused on privacy, robustness, and fairness risks in machine learning systems used for everyday devices and services.

As a member of the Security Research team, her research interests lie at the intersection of Generative AI, privacy and security, fairness, and explainability. She is interested in identifying the risks associated with GenAI powered tools and services for a safer and more reliable consumer experience. Shimaa aspires to bring her knowledge and experience in security and privacy, applied machine learning, systems, and empirical evaluations to real world applications. She has published papers in top-tier conferences including USENIX Security, IEEE Symposium on Security and Privacy, and the Association for the Advancement of Artificial Intelligence (AAAI).

Thesis

Ahmed, S. (2024) Trustworthy User-Machine Interactions, Ph.D. thesis, University of Wisconsin-Madison

Publications

  1. West, Jack, Lea Thiemt, Shimaa Ahmed, Maggie Bartig, Kassem Fawaz, and Suman Banerjee. "A Picture is Worth 500 Labels: A Case Study of Demographic Disparities in Local Machine Learning Models for Instagram and TikTok." In 2024 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA, 2024 pp. 232-232.
  2. Rosenberg, Harrison*, Shimaa Ahmed*, Guruprasad Ramesh*, Kassem Fawaz, and Ramya Korlakai Vinayak. "Limitations of Face Image Generation." In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 13, pp. 14838-14846. 2024
  3. Ahmed, Shimaa, Yash Wani, Ali Shahin Shamsabadi, Mohammad Yaghini, Ilia Shumailov, Nicolas Papernot, and Kassem Fawaz. "Tubes among us: Analog attack on automatic speaker identification." In 32nd USENIX Security Symposium (USENIX Security 23), pp. 265-282. 2023.
  4. Ahmed, Shimaa, Ilia Shumailov, Nicolas Papernot, and Kassem Fawaz. "Towards more robust keyword spotting for voice assistants." In 31st USENIX Security Symposium (USENIX Security 22), pp. 2655-2672. 2022.
  5. Ahmed, Shimaa, Amrita Roy Chowdhury, Kassem Fawaz, and Parmesh Ramanathan. "Preech: A system for {Privacy-Preserving} speech transcription." In 29th USENIX Security Symposium (USENIX Security 20), pp. 2703-2720. 2020.
  6. Ahmed, Shimaa, Mirette Sadek, Abdelhalim Zekry, and Hadia Elhennawy. "Hybrid analog and digital beamforming for space-constrained and energy-efficient massive MIMO wireless systems." In 2017 40th International Conference on Telecommunications and Signal Processing (TSP), pp. 186-189. IEEE, 2017.