skip to main content


Title: Privacy-Preserving Object Detection with Secure Convolutional Neural Networks for Vehicular Edge Computing
With the wider adoption of edge computing services, intelligent edge devices, and high-speed V2X communication, compute-intensive tasks for autonomous vehicles, such as object detection using camera, LiDAR, and/or radar data, can be partially offloaded to road-side edge servers. However, data privacy becomes a major concern for vehicular edge computing, as sensitive sensor data from vehicles can be observed and used by edge servers. We aim to address the privacy problem by protecting both vehicles’ sensor data and the detection results. In this paper, we present vehicle–edge cooperative deep-learning networks with privacy protection for object-detection tasks, named vePOD for short. In vePOD, we leverage the additive secret sharing theory to develop secure functions for every layer in an object-detection convolutional neural network (CNN). A vehicle’s sensor data is split and encrypted into multiple secret shares, each of which is processed on an edge server by going through the secure layers of a detection network. The detection results can only be obtained by combining the partial results from the participating edge servers. We have developed proof-of-concept detection networks with secure layers: vePOD Faster R-CNN (two-stage detection) and vePOD YOLO (single-stage detection). Experimental results on public datasets show that vePOD does not degrade the accuracy of object detection and, most importantly, it protects data privacy for vehicles. The execution of a vePOD object-detection network with secure layers is orders of magnitude faster than the existing approaches for data privacy. To the best of our knowledge, this is the first work that targets privacy protection in object-detection tasks with vehicle–edge cooperative computing.  more » « less
Award ID(s):
1852134 2225229 2113805 2037982 2017564
NSF-PAR ID:
10385749
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Future Internet
Volume:
14
Issue:
11
ISSN:
1999-5903
Page Range / eLocation ID:
316
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The development of communication technologies in edge computing has fostered progress across various applications, particularly those involving vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. Enhanced infrastructure has improved data transmission network availability, promoting better connectivity and data collection from IoT devices. A notable IoT application is with the Intelligent Transportation System (ITS). IoT technology integration enables ITS to access a variety of data sources, including those pertaining to weather and road conditions. Real-time data on factors like temperature, humidity, precipitation, and friction contribute to improved decision-making models. Traditionally, these models are trained at the cloud level, which can lead to communication and computational delays. However, substantial advancements in cloud-to-edge computing have decreased communication relays and increased computational distribution, resulting in faster response times. Despite these benefits, the developments still largely depend on central cloud sources for computation due to restrictions in computational and storage capacity at the edge. This reliance leads to duplicated data transfers between edge servers and cloud application servers. Additionally, edge computing is further complicated by data models predominantly based on data heuristics. In this paper, we propose a system that streamlines edge computing by allowing computation at the edge, thus reducing latency in responding to requests across distributed networks. Our system is also designed to facilitate quick updates of predictions, ensuring vehicles receive more pertinent safety-critical model predictions. We will demonstrate the construction of our system for V2V and V2I applications, incorporating cloud-ware, middleware, and vehicle-ware levels. 
    more » « less
  2. Mobile devices such as drones and autonomous vehicles increasingly rely on object detection (OD) through deep neural networks (DNNs) to perform critical tasks such as navigation, target-tracking and surveillance, just to name a few. Due to their high complexity, the execution of these DNNs requires excessive time and energy. Low-complexity object tracking (OT) is thus used along with OD, where the latter is periodically applied to generate "fresh" references for tracking. However, the frames processed with OD incur large delays, which does not comply with real-time applications requirements. Offloading OD to edge servers can mitigate this issue, but existing work focuses on the optimization of the offloading process in systems where the wireless channel has a very large capacity. Herein, we consider systems with constrained and erratic channel capacity, and establish parallel OT (at the mobile device) and OD (at the edge server) processes that are resilient to large OD latency. We propose Katch-Up, a novel tracking mechanism that improves the system resilience to excessive OD delay. We show that this technique greatly improves the quality of the reference available to tracking, and boosts performance up to 33%. However, while Katch-Up significantly improves performance, it also increases the computing load of the mobile device. Hence, we design SmartDet, a low-complexity controller based on deep reinforcement learning (DRL) that learns to achieve the right trade-off between resource utilization and OD performance. SmartDet takes as input highly-heterogeneous context-related information related to the current video content and the current network conditions to optimize frequency and type of OD offloading, as well as Katch-Up utilization. We extensively evaluate SmartDet on a real-world testbed composed by a JetSon Nano as mobile device and a GTX 980 Ti as edge server, connected through a Wi-Fi link, to collect several network-related traces, as well as energy measurements. We consider a state-of-the-art video dataset (ILSVRC 2015 - VID) and state-of-the-art OD models (EfficientDet 0, 2 and 4). Experimental results show that SmartDet achieves an optimal balance between tracking performance – mean Average Recall (mAR) and resource usage. With respect to a baseline with full Katch-Up usage and maximum channel usage, we still increase mAR by 4% while using 50% less of the channel and 30% power resources associated with Katch-Up. With respect to a fixed strategy using minimal resources, we increase mAR by 20% while using Katch-Up on 1/3 of the frames. 
    more » « less
  3. Connected Autonomous Vehicles (CAVs) have achieved significant improvements in recent years. The CAVs can share sensor data to improve autonomous driving performance and enhance road safety. CAV architecture depends on roadside edge servers for latency-sensitive applications. The roadside edge servers are equipped with high-performance embedded edge computing devices that perform calculations with low power requirements. As the number of vehicles varies over different times of the day and vehicles can request for different CAV applications, the computation requirements for roadside edge computing platform can also vary. Hence, a framework for dynamic deployment of edge computing platforms can ensure CAV applications’ performance and proper usage of the devices. In this paper, we propose R-CAV – a framework for drone-based roadside edge server deployment that provides roadside units (RSUs) based on the computation requirement. Our proof of concept implementation for object detection algorithm using Nvidia Jetson nano demonstrates the proposed framework's feasibility. We posit that the framework will enhance the intelligent transport system vision by ensuring CAV applications’ quality of service. 
    more » « less
  4. The density and complexity of urban environments present significant challenges for autonomous vehicles. Moreover, ensuring pedestrians’ safety and protecting personal privacy are crucial considerations in these environments. Smart city intersections and AI-powered traffic management systems will be essential for addressing these challenges. Therefore, our research focuses on creating an experimental framework for the design of applications that support the secure and efficient management of traffic intersections in urban areas. We integrated two cameras (street-level and bird’s eye view), both viewing an intersection, and a programmable edge computing node, deployed within the COSMOS testbed in New York City, with a central management platform provided by Kentyou. We designed a pipeline to collect and analyze the video streams from both cameras and obtain real-time traffic/pedestrian-related information to support smart city applications. The obtained information from both cameras is merged, and the results are sent to a dedicated dashboard for real-time visualization and further assessment (e.g., accident prevention). The process does not require sending the raw videos in order to avoid violating pedestrians’ privacy. In this demo, we present the designed video analytic pipelines and their integration with Kentyou central management platform. Index Terms—object detection and tracking, camera networks, smart intersection, real-time visualization 
    more » « less
  5. The vehicular fog is a relatively new computing paradigm where fog computing works with the vehicular network. It provides computation, storage, and location-aware services with low latency to the vehicles in close proximity. A vehicular fog network can be formed on-the-fly by adding underutilized or unused resources of nearby parked or moving vehicles. Interested vehicles can outsource their resources or data by being added to the vehicular fog network while maintaining proper security and privacy. Client vehicles can use these resources or services for performing computation-intensive tasks, storing data, or getting crowdsource reports through the proper secure and privacy-preserving communication channel. As most vehicular network applications are latency and location sensitive, fog is more suitable than the cloud because of the capability of performing calculations with low latency, location awareness, and the support of mobility. Architecture, security, and privacy models of vehicular fog are not well defined and widely accepted yet as it is in its early stage. In this paper, we have analyzed existing studies on vehicular fog to determine the requirements and issues related to the architecture, security, and privacy of vehicular fog computing. We have also identified and highlighted the open research problems in this promising area. 
    more » « less