CPS: Small: Collaborative Research: SecureNN: Design of Secured Autonomous Cyber-Physical Systems Against Adversarial Machine Learning Attacks

CPS：小型：协作研究：SecureNN：针对对抗性机器学习攻击的安全自主网络物理系统的设计

• 批准号: 1932351
• 负责人: Xue Lin
• 金额: $ 25万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-11-01 至 2024-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1932351&HistoricalAwards=false
• 关键词: CPS; Small; Collaborative; Research; SecureNN

Cyber-physical systems such as self-driving cars, drones, and intelligent transportation rely heavily on machine learning techniques for ever-increasing levels of autonomy. In the example of autonomous vehicles, deep learning or deep neural networks can be employed for perception, sensor fusion, prediction, planning, and control tasks. However powerful such machine learning techniques have become, they also expose a new attack surface, which may lead to vulnerability to adversarial attacks and potentially harmful consequences in security- and safety-critical scenarios. This project investigates adversarial machine learning challenges faced by autonomous cyber-physical systems with the aim of formulating defense strategies. The project will collaborate with the Center for STEM (Science, Technology, Engineering and Math) Education at Northeastern University and the Office of Access and Inclusion Center at University of California at Irvine to engage undergraduates, women, and minority students in independent research projects.This project is composed of two interdependent research thrusts, one for investigating adversarial attacks and one for devising countermeasures, aiming to secure the key deep learning-equipped software components of autonomous cyber-physical systems, such as perception, obstacle prediction, and vehicle planning and control. The main deep learning techniques of interest to autonomous cyber-physical systems include convolutional neural networks for detection, recurrent neural networks for prediction, and deep reinforcement learning for control. The technical innovations of the project include ADMM (Alternating Direction Method of Multipliers) based attack generation, concurrent adversarial training and model compression, and multi-sourced defense schemes incorporating adversarial training and ensemble learning. This project will implement and evaluate the proposed attack and defense approaches on real-world prototypes of autonomous cyber-physical systems for autonomous vehicles and unmanned aerial vehicles in the investigators' labs. The investigators will release all the developed models, algorithms, and software to GitHub to facilitate community usage.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

自动驾驶汽车、无人机和智能交通等网络物理系统严重依赖机器学习技术来实现不断提高的自主水平。在自动驾驶汽车的例子中，深度学习或深度神经网络可以用于感知、传感器融合、预测、规划和控制任务。无论这种机器学习技术变得多么强大，它们也暴露了一个新的攻击面，这可能导致容易受到对抗性攻击，并在安全和安全关键场景中产生潜在的有害后果。该项目研究自主网络物理系统所面临的对抗性机器学习挑战，旨在制定防御策略。该项目将与东北大学STEM（科学、技术、工程和数学）教育中心以及加州大学欧文分校的准入和包容中心办公室合作，让本科生、女性和少数族裔学生参与独立研究项目。该项目由两个相互依存的研究重点组成，一个用于调查对抗性攻击，另一个用于设计对策，旨在确保自主网络物理系统中配备深度学习的关键软件组件的安全，如感知、障碍物预测、车辆规划和控制。自主网络物理系统感兴趣的主要深度学习技术包括用于检测的卷积神经网络、用于预测的循环神经网络和用于控制的深度强化学习。该项目的技术创新包括基于ADMM（乘数交替方向法）的攻击生成、并发对抗训练和模型压缩，以及结合对抗训练和集成学习的多源防御方案。该项目将在研究人员实验室的自动驾驶车辆和无人驾驶飞行器的自主网络物理系统的真实原型上实施和评估拟议的攻击和防御方法。研究人员将把所有开发的模型、算法和软件发布到GitHub，以方便社区使用。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Pruning Parameterization with Bi-level Optimization for Efficient Semantic Segmentation on the Edge

• DOI: 10.1109/cvpr52729.2023.01478
• 发表时间: 2023-06
• 期刊: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Changdi Yang;Pu Zhao;Yanyu Li;Wei Niu;Jiexiong Guan;Hao Tang;Minghai Qin;Bin Ren;Xue Lin;Yanzhi Wang

Intrinsic Examples: Robust Fingerprinting of Deep Neural Networks

• 发表时间: 2021
• 期刊: International Journal of Molecular Sciences
• 影响因子: 5.6
• 作者: Siyue Wang;Pu Zhao;Xiao Wang;S. Chin;T. Wahl;Yunsi Fei;Qi Alfred Chen;Xue Lin

RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices

RT3D：在移动设备上实现 3D 卷积神经网络的实时执行

• 发表时间: 2021
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Niu, Wei;Sun, Mengshu;Li, Zhengang;Chen, Jou-An;Guan, Jiexiong;Shen, Xipeng;Wang, Yanzhi;Liu, Sijia;Lin, Xue;Ren, Bin
• 通讯作者: Ren, Bin

ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization

• 发表时间: 2019-10
• 期刊: ArXiv
• 作者: Xiangyi Chen;Sijia Liu;Kaidi Xu;Xingguo Li;Xue Lin;Mingyi Hong;David Cox

Neural Pruning Search for Real-Time Object Detection of Autonomous Vehicles

用于自动驾驶车辆实时目标检测的神经剪枝搜索

• DOI: 10.1109/dac18074.2021.9586163
• 发表时间: 2021
• 期刊: Proceedings of the 58th Design Automation Conference (DAC
• 作者: Zhao, Pu;Yuan, Geng;Cai, Yuxuan;Niu, Wei;Liu, Qi;Wen, Wujie;Ren, Bin;Wang, Yanzhi;Lin, Xue
• 通讯作者: Lin, Xue