相关实验视频
Updated: Sep 17, 2025

Photorealistic Learned Landscapes for Augmented Reality
Published on: June 27, 2025
强化嵌入式主动防御:利用适应性交互在敌对的3D环境中实现强大的视觉感知
一个新的主动防御框架,强化嵌入式主动防御 (REIN-EAD),增强3D视觉感知系统对抗对手攻击的稳定性. 它使用自适应式探索和交互来最大限度地减少预测错误,并在动态环境中提高安全性.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 机器人技术 机器人技术 机器人技术
背景情况:
- 敌对攻击威胁到自动驾驶等关键应用中的3D视觉感知系统.
- 当前的防御手段 (如对抗性训练) 往往是被动的,并与动态的3D环境作斗争.
- 深度神经网络 (DNN) 易受通过复杂场景中的对抗补丁和对象的操纵.
研究的目的:
- 引入强化嵌入式主动防御 (REIN-EAD),这是一个积极的框架,用于提高3D对抗环境中的DNN稳定性.
- 开发一种适应性防御机制,探索和与环境相互作用.
- 提高视觉感知系统对复杂攻击的可靠性.
主要方法:
- REIN-EAD采用多步客观平衡预测准确性和最小化.
- 一个以不确定性为导向的奖励塑造机制促进了有效的政策更新.
- 该框架将主动政策学习与体现场互动相结合.
主要成果:
- 在各种任务中,REIN-EAD显著降低了对抗性攻击的成功率.
- 在防御过程中保持标准准确性.
- 该框架展示了对未见和适应性攻击的强有力的概括性.
结论:
- REIN-EAD提供了一个可扩展和可适应的解决方案,用于在动态3D环境中保护基于DNN的感知系统.
- 积极主动和体现的方法克服了被动防御策略的局限性.
- 该框架适用于现实世界的应用,包括3D对象分类,人脸识别和自动驾驶.
更多相关视频
03:31Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
06:20Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
Published on: December 6, 2024
相关概念视频
Three-Dimensional Force System:Problem Solving
To solve a three-dimensional force system, first resolve each force into its respective scalar components. Do this using...
Collisions in Multiple Dimensions: Problem Solving
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
Collisions in Multiple Dimensions: Introduction
Three-Dimensional Force System
Two-Dimensional Force System: Problem Solving
The first step to solving a two-dimensional force system problem is to draw a free-body diagram of the object under consideration. This diagram helps identify all the external forces acting on the object, including their...
Reinforcements in Concrete