10 papers
ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments
Mansi Phute, Alexander Greenhalgh, Matthew Hull +8
Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized. Bridging simulation and…
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.…
Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection
Willian T. Lunardi, Samridha Shrestha, Martin Andreoni
Out-of-distribution (OOD) detection for time-series data remains comparatively underexplored compared to vision and language, with a limited principled understanding of how supervi…
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…
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…
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…