Robotics, automation, and related Artificial Intelligence (AI) systems have
become pervasive bringing in concerns related to security, safety, accuracy,
and trust. With growing dependency on physical robots that work in close
proximity to humans, the security of these systems is becoming increasingly
important to prevent cyber-attacks that could lead to privacy invasion,
critical operations sabotage, and bodily harm. The current shortfall of
professionals who can defend such systems demands development and integration
of such a curriculum. This course description includes details about seven
self-contained and adaptive modules on "AI security threats against pervasive
robotic systems". Topics include: 1) Introduction, examples of attacks, and
motivation; 2) - Robotic AI attack surfaces and penetration testing; 3) -
Attack patterns and security strategies for input sensors; 4) - Training
attacks and associated security strategies; 5) - Inference attacks and
associated security strategies; 6) - Actuator attacks and associated security
strategies; and 7) - Ethics of AI, robotics, and cybersecurity.

物理机器人近距离工作，科技安全的威胁引起人们担忧。现今缺少专业人士来保护这些系统，因此需要相应的课程来开发和集成。该课程包括七个自包含的模块，旨在对普及的机器人系统进行人工智能安全威胁防御与训练。

普适机器人系统的 AI 安全威胁：下一代网络安全人才的课程

AI Security Threats against Pervasive Robotic Systems: A Course for Next Generation Cybersecurity Workforce

Through many recent successes in simulation, model-free reinforcement
learning has emerged as a promising approach to solving continuous control
robotic tasks. The research community is now able to reproduce, analyze and
build quickly on these results due to open source implementations of learning
algorithms and simulated benchmark tasks. To carry forward these successes to
real-world applications, it is crucial to withhold utilizing the unique
advantages of simulations that do not transfer to the real world and experiment
directly with physical robots. However, reinforcement learning research with
physical robots faces substantial resistance due to the lack of benchmark tasks
and supporting source code. In this work, we introduce several reinforcement
learning tasks with multiple commercially available robots that present varying
levels of learning difficulty, setup, and repeatability. On these tasks, we
test the learning performance of off-the-shelf implementations of four
reinforcement learning algorithms and analyze sensitivity to their
hyper-parameters to determine their readiness for applications in various
real-world tasks. Our results show that with a careful setup of the task
interface and computations, some of these implementations can be readily
applicable to physical robots. We find that state-of-the-art learning
algorithms are highly sensitive to their hyper-parameters and their relative
ordering does not transfer across tasks, indicating the necessity of re-tuning
them for each task for best performance. On the other hand, the best
hyper-parameter configuration from one task may often result in effective
learning on held-out tasks even with different robots, providing a reasonable
default. We make the benchmark tasks publicly available to enhance
reproducibility in real-world reinforcement learning.

通过在多个商业机器人上实施我们引入的多个强化学习任务，通过对其四种增强学习算法的学习性能进行测试并分析其对超参数的灵敏度，揭示出这些算法的实际应用性。我们发现现代学习算法对超参数非常敏感，为了获得最佳性能需要为每个任务重新调整参数。