1 citations · 1 across the 14 of their papers we have counts for
7 papers · 1 filter
Toward an Intrusion Detection System for a Virtualization Framework in Edge Computing
Everton de Matos, Hazaa Alameri, Willian Tessaro Lunardi +2
Edge computing pushes computation closer to data sources, but it also expands the attack surface on resource-constrained devices. This work explores the deployment of the Lightweig…
UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks
Mansi Phute, Matthew Hull, Haoran Wang +6
Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions.…
ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages
Matthew Hull, Haoyang Yang, Pratham Mehta +8
As 3D Gaussian Splatting (3DGS) gains rapid adoption in safety-critical tasks for efficient novel-view synthesis from static images, how might an adversary tamper images to cause h…
Graph Neural Networks for Jamming Source Localization
Dania Herzalla, Willian T. Lunardi, Martin Andreoni
Graph-based learning provides a powerful framework for modeling complex relational structures; however, its application within the domain of wireless security remains significantly…
3D Gaussian Splat Vulnerabilities
Matthew Hull, Haoyang Yang, Pratham Mehta +8
With 3D Gaussian Splatting (3DGS) being increasingly used in safety-critical applications, how can an adversary manipulate the scene to cause harm? We introduce CLOAK, the first at…
Secure Safety Filter: Towards Safe Flight Control under Sensor Attacks
Xiao Tan, Junior Sundar, Renzo Bruzzone +5
Modern autopilot systems are prone to sensor attacks that can jeopardize flight safety. To mitigate this risk, we proposed a modular solution: the secure safety filter, which exten…
Contrastive Representation Modeling for Anomaly Detection
Willian T. Lunardi, Abdulrahman Banabila, Dania Herzalla +1
Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategi…