Ph.D. Electrical and Computer Engineering, 2017 - Present
University of Wisconsin-Madison
M.S. Electrical and Computer Engineering, 2017
Ain Shams University, Cairo, Egypt
I am a Ph.D. student at the University of Wisconsin-Madison, Electrical and Computer Engineering Department. My research interests lie at the intersection of Privacy, Systems, Signal Processing, and Machine Learning. Currently, I am advised by Kassem Fawaz working on the design of privacy enhancing systems for emerging technologies. Previously, I obtained my M.Sc. degree from my alma mater Ain Shams University, Cairo, Egypt in 2017. My background spans different topics including wireless communications, signal processing, and Analog and RF IC design.
Oct 2021: Our work on the robustness of keyword spotting for voice assistants will be appearing at USENIX Security, 2022.
June 2021: I will be interning at Microsoft Cognitive AI Services – Speech Team, Redmond under Jian Wu and Anthony Stark. I will work on the robustness of the keyword spotting systems.
In this project, we propose a system to enhance the robustness of keyword spotting systems for voice assistants. We propose EKOS (Ensemble for KeywOrd Spotting) which leverages the semantics of the KWS task to defend against both accidental and adversarial activations. EKOS incorporates spatial redundancy from the acoustic environment at training and inference time to minimize distribution drifts responsible for accidental activations. It also exploits a physical property of speech (its redundancy at different harmonics) to deploy an ensemble of models trained on different harmonics and provably force the adversary to modify more of the frequency spectrum to obtain adversarial examples.
Our evaluation shows that EKOS increases the cost of adversarial activations while preserving the natural accuracy. We validate the performance of EKOS with over-the-air experiments on commodity devices and commercial voice assistants; we find that EKOS improves the precision of the KWS task in non-adversarial settings.
Shimaa Ahmed, Ilia Shumailov, Nicolas Papernot, and Kassem Fawaz. Towards More Robust Keyword Spotting for Voice Assistants. In 30th USENIX Security Symposium (USENIX Security 22), Aug 2022. [pdf]
In this project, we study and quantify the utility-privacy trade-offs between online (Cloud-based) and offline speech transcription services. Cloud-based transcription services pose serious privacy threats as speech is a rich source of sensitive acoustic and textual information. Although offline systems eliminates the privacy risks, we found that its transcription performance is inferior to that of cloud-based systems, especially for real-world use cases.
In this project, we propose Pr$\epsilon\epsilon$ch, an end-to-end speech transcription system which lies at an intermediate point in the privacy-utility spectrum. It relies on cloud-based services to transcribe a speech file after applying a series of privacy-preserving operations on the user’s side. These operations protect the acoustic features of the speakers’ voices and protect the privacy of the textual content at an improved performance relative to offline system. Additionally, Pr$\epsilon\epsilon$ch provides several control knobs to allow customizable utility-usability-privacy trade-off. We perform a comprehensive evaluation of Pr$\epsilon\epsilon$ch, using diverse real-world datasets, that demonstrates its effectiveness. Pr$\epsilon\epsilon$ch provides transcriptions at a 2% to 32.25% (mean 17.34%) relative improvement in word error rate over Deep Speech, while fully obfuscating the speakers’ voice biometrics and allowing only a differentially private view of the textual content. A demo of Pr$\epsilon\epsilon$ch can be found here.
Shimaa Ahmed, Amrita Roy Chowdhury, Kassem Fawaz, and Parmeswaran Ramanathan. Preech: A system for privacy-preserving speech transcription. In 29th USENIX Security Symposium (USENIX Security 20), pages 2703–2720. USENIX Association, Aug. 2020. [paper]
Towards More Robust Keyword Spotting for Voice Assistants. Shimaa Ahmed, Ilia Shumailov, Nicolas Papernot, Kassem Fawaz. USENIX Security, 2022
Pr$\epsilon\epsilon$ch: A System for Privacy-Preserving Speech Transcription.
Shimaa Ahmed, Amrita Roy Chowdhury, Kassem Fawaz, Parmesh Ramanathan. USENIX Security, 2020
ahmed27_AT_wisc.edu