8 papers
Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models
Amira Guesmi, Muhammad Shafique
Vision-language models (VLMs) have recently shown remarkable capabilities in visual understanding and generation, but remain vulnerable to adversarial manipulations of visual conte…
PatchBlock: A Lightweight Defense Against Adversarial Patches for Embedded EdgeAI Devices
Nandish Chattopadhyay, Abdul Basit, Amira Guesmi +3
Adversarial attacks pose a significant challenge to the reliable deployment of machine learning models in EdgeAI applications, such as autonomous driving and surveillance, which re…
DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defense
Amira Guesmi, Muhammad Shafique
Deep neural networks remain highly vulnerable to adversarial examples, and most defenses collapse once gradients can be reliably estimated. We identify \emph{gradient consensus} --…
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…
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…
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…