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: 1932464
• 负责人: Qi Chen
• 金额: $ 25万
• 依托单位: University of California-Irvine
• 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 2023-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1932464&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不断提高自主水平。以自动驾驶汽车为例，深度学习或深度神经网络可用于感知、传感器融合、预测、规划和控制任务。无论此类机器学习技术变得多么强大，它们也暴露了新的攻击面，这可能导致容易遭受对抗性攻击，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）教育中心和加州大学欧文分校访问和包容中心办公室合作，吸引本科生、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赖的研究重点组成，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的关键深度学习软件组件的安全，例如感知、障碍物预测和车辆规划和控制。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机的自主网络物理系统的真实原型上实施和评估所提出的攻击和防御方法。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 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，认为值得支持。

项目成果

Doppelganger Test Generation for Revealing Bugs in Autonomous Driving Software

用于揭示自动驾驶软件中的错误的分身测试生成

• 发表时间: 2023-01
• 期刊: International Conference on Software Engineering (ICSE
• 作者: Huai, Yuqi;Chen, Yuantianyi;Almanee, Sumaya;Ngo, Tuan;Liao, Xiang;Wan, Ziwen;Chen, Qi Alfred;Garcia, Joshua
• 通讯作者: Garcia, Joshua

WIP: Practical Removal Attacks on LiDAR-based Object Detection in Autonomous Driving

WIP：自动驾驶中基于 LiDAR 的目标检测的实际删除攻击

• 发表时间: 2023-01
• 期刊: ISOC Symposium on Vehicle Security and Privacy (VehicleSec
• 作者: Sato, Takami;Hayakawa, Yuki;Suzuki, Ryo;Shiiki, Yohsuke;Yoshioka, Kentaro;Chen, Qi Alfred
• 通讯作者: Chen, Qi Alfred

On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles

自动驾驶车辆轨迹预测的对抗鲁棒性

• 发表时间: 2022-01
• 期刊: IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR
• 作者: Zhang, Qingzhao;Hu, Shengtuo;Sun, Jiachen;Chen, Qi Alfred;Mao, Z. Morley
• 通讯作者: Mao, Z. Morley

WIP: Towards the Practicality of the Adversarial Attack on Object Tracking in Autonomous Driving

WIP：实现自动驾驶中目标跟踪的对抗性攻击的实用性

• 发表时间: 2023-01
• 期刊: ISOC Symposium on Vehicle Security and Privacy (VehicleSec
• 作者: Ma, Chen;Wang, Ningfei;Chen, Qi Alfred;Shen, Chao
• 通讯作者: Shen, Chao

Too Afraid to Drive: Systematic Discovery of Semantic DoS Vulnerability in Autonomous Driving Planning under Physical-World Attacks

太害怕开车：物理世界攻击下自动驾驶规划中语义 DoS 漏洞的系统发现

• 发表时间: 2022-01
• 期刊: ISOC Network and Distributed Systems Security (NDSS
• 作者: Wan, Ziwen;Shen, Junjie;Chuang, Jalen;Xia, Xin;Garcia, Joshua;Ma, Jiaqi;Chen, Qi Alfred
• 通讯作者: Chen, Qi Alfred