关于自动驾驶实时语义细分模型的现实世界对抗性稳定性
IEEE transactions on neural networks and learning systems
|October 2, 2023
概括
现实世界的对抗性补丁威胁到自动驾驶AI. 本研究评估了语义细分对数字,模拟和物理攻击的稳定性,并提出了新的攻击和防御方法.
科学领域:
- 计算机视觉 计算机视觉
- 深度学习安全 深度学习安全
背景情况:
- 现实世界的对抗性示例 (RWAE),通常是补丁,在安全关键的应用中对深度学习模型构成重大风险,例如自动驾驶.
- 语义细分 (SS) 模型特别容易受到这些攻击,影响视觉感知系统.
研究的目的:
- 对各种对抗性补丁类型 (数字,模拟,物理) 的语义细分模型的稳定性进行全面评估.
- 引入新的方法来加强对抗性攻击,并改善SS模型的补丁检测.
主要方法:
- 开发了一种新的损失函数,以提高攻击者错误分类像素的有效性.
- 引入了改进的攻击策略,以提高对补丁放置的期望对转换 (EOT) 方法的预期.
- 扩展和优化SS模型的最先进的对抗补丁检测方法,实现实时性能.
主要成果:
- 敌对的补丁攻击,无论是数字还是现实世界,都明显影响SS模型的性能.
- 这些攻击的影响经常局部化在图像中的补丁位置周围.
- 拟议的检测方法在现实场景中展示了实时功能.
结论:
- 虽然对抗性补丁构成明显的威胁,但它们的局部影响表明实时SS模型的空间稳定性存在潜在漏洞.
- 需要进一步的研究来理解和减轻对自动驾驶感知系统的对抗性攻击的空间影响.
更多相关视频
04:48Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.8K
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
261
相关概念视频
Stereotype Content Model
14.7K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.7K
Force Classification
1.2K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.2K
Survival Tree
105
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
105
