activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2025

TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularization

Amira Guesmi, Bassem Ouni, Muhammad Shafique

Adversarial transferability remains a critical challenge in evaluating the robustness of deep neural networks. In security-critical applications, transferability enables black-box…

cs.CV2025

TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks

Amira Guesmi, Bassem Ouni, Muhammad Shafique

Quantized Neural Networks (QNNs) are increasingly deployed in edge and resource-constrained environments due to their efficiency in computation and memory usage. While shown to dis…

cs.CV2025

ShrinkBox: Backdoor Attack on Object Detection to Disrupt Collision Avoidance in Machine Learning-based Advanced Driver Assistance Systems

Muhammad Zaeem Shahzad, Muhammad Abdullah Hanif, Bassem Ouni +1

Advanced Driver Assistance Systems (ADAS) significantly enhance road safety by detecting potential collisions and alerting drivers. However, their reliance on expensive sensor tech…

cs.CV2025

Breaking the Limits of Quantization-Aware Defenses: QADT-R for Robustness Against Patch-Based Adversarial Attacks in QNNs

Amira Guesmi, Bassem Ouni, Muhammad Shafique

Quantized Neural Networks (QNNs) have emerged as a promising solution for reducing model size and computational costs, making them well-suited for deployment in edge and resource-c…

cs.CV2025

A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challenges

Nandish Chattopadhyay, Abdul Basit, Bassem Ouni +1

Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a v…

cs.CV2024

SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applications

Amira Guesmi, Muhammad Abdullah Hanif, Ihsen Alouani +2

Monocular depth estimation (MDE) has advanced significantly, primarily through the integration of convolutional neural networks (CNNs) and more recently, Transformers. However, con…