5 papers
Seeing at the Edge: Energy Characterization of Vision-Language Model Inference on Edge Platforms
Junlin Liao, Harshit Kondle, Di Liu +1
Vision-language models (VLMs) are moving onto edge devices, but little is known about how much energy they draw on single-board computers with NPU or GPU accelerators, or where tha…
TrackShield: An Efficient Runtime Defense Against Availability Attacks on High-Performance Real-Time Multi-Object Tracking
Zonghua Gu, Julian Singh-Smith, Junlin Liao +1
High-performance camera-based perception pipelines must sustain per-frame real-time budgets on resource-constrained embedded GPU platforms. Availability attacks such as SlowTrack i…
Deep Learning Latency Attacks and Defenses: A Cross-Domain Survey of Availability Threats
Zonghua Gu, Zeyu Gao, Amin Saremi +1
Adversarial machine learning has focused mainly on integrity, but availability is an increasingly consequential complement. Latency attacks (also energy-latency attacks) increase i…
TrackFlood: Relocating Latency Attacks from NMS-Free Detectors to Real-Time Trackers
Zonghua Gu, Julian Singh-Smith, Junlin Liao +2
We consider latency attacks on object detectors, where the attacker's goal is not to corrupt a prediction but to make the system fail to respond in time, targeting real-time applic…
AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control
Peng Xu, Zhengnan Deng, Jiayan Deng +2
Vision-Language Navigation (VLN) for Unmanned Aerial Vehicles (UAVs) demands complex visual interpretation and continuous control in dynamic 3D environments. Existing hierarchical…