5 citations · 6 across the 15 of their papers we have counts for
16 papers
Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents
Halima Bouzidi, Mboutidem Ekemini Mkpong, Mohammad Abdullah Al Faruque
Multimodal AI agents increasingly rely on persistent long-term memory to ground generation in past visual and textual episodes. We show that unconditional trust in visual data crea…
Off the Rails: Hijacking the Scoring Head in Generative End-to-End Driving Planners with Safety-Violating Adversarial Perturbations
Halima Bouzidi, Mboutidem Ekemini Mkpong, Haoyu Liu +1
Generative models have recently seen rapid adoption in End-to-End (E2E) autonomous driving (AD), with diffusion-based denoising and vocabulary-based retrieval becoming the dominant…
Glitch in the Sky: Exploiting Voltage Fault Injection in UAV Flight Controllers
Yun-Ping Hsiao, Yanda Li, Youssef Gamal +2
As Cyber-Physical Systems (CPS) become increasingly pervasive and autonomous, ensuring the resilience of their embedded logic is critical to maintaining safety and integrity. Among…
Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation
Halima Bouzidi, Haoyu Liu, Yonatan Gizachew Achamyeleh +2
Recent Tracking-by-Query-Propagation (TBP) methods have advanced Multi-Object Tracking (MOT) by enabling end-to-end (E2E) pipelines with long-range temporal modeling. However, this…
FlyTrap: Physical Distance-Pulling Attack Towards Camera-based Autonomous Target Tracking Systems
Shaoyuan Xie, Mohamad Habib Fakih, Junchi Lu +6
Autonomous Target Tracking (ATT) systems, especially ATT drones, are widely used in applications such as surveillance, border control, and law enforcement, while also being misused…
Invisible Ears at Your Fingertips: Acoustic Eavesdropping via Mouse Sensors
Mohamad Fakih, Rahul Dharmaji, Youssef Mahmoud +2
Modern optical mouse sensors, with their advanced precision and high responsiveness, possess an often overlooked vulnerability: they can be exploited for side-channel attacks. This…
See No Evil: Adversarial Attacks Against Linguistic-Visual Association in Referring Multi-Object Tracking Systems
Halima Bouzidi, Haoyu Liu, Mohammad Abdullah Al Faruque
Language-vision understanding has driven the development of advanced perception systems, most notably the emerging paradigm of Referring Multi-Object Tracking (RMOT). By leveraging…
LLM4CVE: Enabling Iterative Automated Vulnerability Repair with Large Language Models
Mohamad Fakih, Rahul Dharmaji, Halima Bouzidi +3
Software vulnerabilities continue to be ubiquitous, even in the era of AI-powered code assistants, advanced static analysis tools, and the adoption of extensive testing frameworks.…
SnatchML: Hijacking ML models without Training Access
Mahmoud Ghorbel, Halima Bouzidi, Ioan Marius Bilasco +1
Model hijacking can cause significant accountability and security risks since the owner of a hijacked model can be framed for having their model offer illegal or unethical services…
SONATA: Self-adaptive Evolutionary Framework for Hardware-aware Neural Architecture Search
Halima Bouzidi, Smail Niar, Hamza Ouarnoughi +1
Recent advancements in Artificial Intelligence (AI), driven by Neural Networks (NN), demand innovative neural architecture designs, particularly within the constrained environments…
Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices
Mohamed Imed Eddine Ghebriout, Halima Bouzidi, Smail Niar +1
The recent surge of interest surrounding Multimodal Neural Networks (MM-NN) is attributed to their ability to effectively process and integrate multiscale information from diverse…
MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment
Mohanad Odema, Halima Bouzidi, Hamza Ouarnoughi +2
Graph Neural Networks (GNNs) are becoming increasingly popular for vision-based applications due to their intrinsic capacity in modeling structural and contextual relations between…
Treasure What You Have: Exploiting Similarity in Deep Neural Networks for Efficient Video Processing
Hadjer Benmeziane, Halima Bouzidi, Hamza Ouarnoughi +2
Deep learning has enabled various Internet of Things (IoT) applications. Still, designing models with high accuracy and computational efficiency remains a significant challenge, es…
Map-and-Conquer: Energy-Efficient Mapping of Dynamic Neural Nets onto Heterogeneous MPSoCs
Halima Bouzidi, Mohanad Odema, Hamza Ouarnoughi +2
Heterogeneous MPSoCs comprise diverse processing units of varying compute capabilities. To date, the mapping strategies of neural networks (NNs) onto such systems are yet to exploi…
HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling
Halima Bouzidi, Mohanad Odema, Hamza Ouarnoughi +2
Dynamic neural networks (DyNNs) have become viable techniques to enable intelligence on resource-constrained edge devices while maintaining computational efficiency. In many cases,…
Performance Prediction for Convolutional Neural Networks in Edge Devices
Halima Bouzidi, Hamza Ouarnoughi, Smail Niar +1
Running Convolutional Neural Network (CNN) based applications on edge devices near the source of data can meet the latency and privacy challenges. However due to their reduced comp…