快速对抗训练与适应式步骤大小
概括
敌对训练可以防御攻击,但速度很慢. 这项研究引入了适应式步尺寸 (ATAS) 的对抗性训练,可以减轻灾难性的过拟合,并通过调整步尺寸以适应实例梯度规范来提高稳健的准确性.
科学领域:
- 机器学习 机器学习
- 计算机视觉 计算机视觉
- 网络安全 网络安全
背景情况:
- 对抗训练对抗攻击有效,但训练时间较慢,阻碍了对大型数据集的可扩展性.
- 目前的加速方法使用单步攻击,冒着灾难性的过度装配和强度损失的风险.
- 灾难性过拟合与特定实例的特征有关,特别是输入梯度规范.
研究的目的:
- 在对抗训练中调查灾难性过拟合的依赖实例的性质.
- 提出一种新的方法,即适应式步尺大小 (ATAS) 的对抗性训练,以应对灾难性过度装配.
- 为了证明ATAS在提高训练速度和强大的准确性方面的有效性.
主要方法:
- 分析实例梯度规范与灾难性过拟合之间的关系.
- 开发ATAS,它采用一个对实例的适应性步骤大小与输入梯度规范成反比例.
- 进行理论分析以证明ATAS与非适应性方法相比更快地趋同.
主要成果:
- 在CIFAR10,CIFAR100和ImageNet数据集上进行实证验证.
- ATAS有效地缓解了各种对抗预算的灾难性过度填充.
- 与现有方法相比,ATAS 实现了更高的可靠精度.
结论:
- 对抗训练中的灾难性过拟合是取决于实例的,并且与梯度规范相关.
- ATAS为灾难性过度装配提供了可扩展和有效的解决方案,增强了对手的稳定性.
- 拟议的方法为高效和强大的对抗训练提供了一个有希望的方向.
相关概念视频
01:19Survival Tree
88
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...
88
01:14Avoidance Learning and Learned Helplessness
1.7K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
1.7K
01:27Associative Learning
412
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
412
02:07Improving Translational Accuracy
11.4K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.4K