3 papers
cs.LG2025
Quantitative Analysis of Deeply Quantized Tiny Neural Networks Robust to Adversarial Attacks
Idris Zakariyya, Ferheen Ayaz, Mounia Kharbouche-Harrari +4
Reducing the memory footprint of Machine Learning (ML) models, especially Deep Neural Networks (DNNs), is imperative to facilitate their deployment on resource-constrained edge dev…
cs.CV2025
The State of Post-Hoc Local XAI Techniques for Image Processing: Challenges and Motivations
Rech Leong Tian Poh, Sye Loong Keoh, Liying Li
As complex AI systems further prove to be an integral part of our lives, a persistent and critical problem is the underlying black-box nature of such products and systems. In pursu…
cs.LG2023
Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks
Ferheen Ayaz, Idris Zakariyya, José Cano +4
Reducing the memory footprint of Machine Learning (ML) models, particularly Deep Neural Networks (DNNs), is essential to enable their deployment into resource-constrained tiny devi…