Research
ICLR · 2026
Amira Guesmi, Bassem Ouni, Muhammad Shafique
A defense framework that disrupts semantic and gradient alignment across bit-widths to prevent patch transferability in quantized neural networks.
ASPLOS · 2021
Amira Guesmi, Ihsen Alouani, Khaled N. Khasawneh, Mouna Baklouti, Tarek Frikha, Mohamed Abid, Nael Abu-Ghazaleh
A hardware-level defense that leverages approximate computing to improve robustness of CNNs against adversarial attacks while reducing energy consumption.
ICLR · 2026
Amira Guesmi, Muhammad Shafique
A stochastic differentiable defense framework that breaks gradient consensus via divergent responses across filtered transformations.
arXiv · 2025
Amira Guesmi, Bassem Ouni, Muhammad Shafique
A framework that significantly improves black-box adversarial attack transferability from Vision Transformers via spectral and semantic regularization.
ICCV 2025 · 2025
Nandish Chattopadhyay, Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, Muhammad Shafique
A defense framework that detects and suppresses adversarial patch artifacts via feature outlier modeling and dimensionality reduction.
CVPR · 2024
Amira Guesmi, Ruitian Ding, Muhammad Abdullah Hanif, Ihsen Alouani, Muhammad Shafique
A dynamic adversarial patch that adapts spatially and temporally to effectively evade modern person detection models under realistic conditions.
IROS · 2024
Amira Guesmi, Muhammad Abdullah Hanif, Ihsen Alouani, Bassem Ouni, Muhammad Shafique
A shape-aware adversarial patch that disrupts monocular depth estimation in autonomous navigation systems.