具有特征不确定性学习和标签嵌入的对抗性强大的神经网络
Ran Wang1, Haopeng Ke2, Meng Hu3
1School of Mathematical Science, Shenzhen University, Shenzhen, 518060, China; Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen, 518060, China; Shenzhen Key Laboratory of Advanced Machine Learning and Applications, Shenzhen University, Shenzhen, 518060, China.
概括
本研究介绍了Margin-SNN,这是一种使用随机神经网络 (SNN) 来增强深度神经网络 (DNN) 的对抗性强度的新型防御方法. 边缘-SNN通过学习特征不确定性和嵌入标签来提高阶级分离的性能来提高安全性,优于标准对抗训练.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 计算机视觉 计算机视觉
背景情况:
- 深度神经网络 (DNN) 面临着严重的安全风险,原因是敌对的例子.
- 现有的防御机制往往需要复杂的对抗训练,增加计算成本.
研究的目的:
- 提出一种新的防御方法,即边缘SNN,以提高DNN的对抗性强度.
- 提高DNN安全性,而不会在培训期间引入对抗性信息,提供更有效的解决方案.
主要方法:
- 边缘SNN使用随机神经网络 (SNN) 具有两个关键模块:特征不确定性学习和标签嵌入.
- 特性不确定性模块在潜空间中引入分布式表示,通过变异信息瓶促进类内紧性.
- 标签嵌入模块将标签映射到功能空间中,通过扩大类之间的边缘来增强类间的分离性.
主要成果:
- 在MNIST,FASHION MNIST,CIFAR10,CIFAR100和SVHN数据集上进行了广泛的实验,证明了Margin-SNN的优越防御能力.
- 拟议的方法通过标准培训实现了更好的对抗稳定性,证明比对抗培训更有效.
结论:
- 边缘SNN提供了一种有效和高效的方法来加强DNN的对抗性稳定性.
- 该方法通过利用特征不确定性和标签语义来提高安全性,为更安全的AI系统铺平了道路.
相关概念视频
Uncertainty: Overview
555
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
555
Propagation of Uncertainty from Random Error
691
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
691
Propagation of Uncertainty from Systematic Error
522
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
522
Uncertainty: Confidence Intervals
4.1K
The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...
4.1K
Associative Learning
378
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...
378
Uncertainty in Measurement: Accuracy and Precision
73.7K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
73.7K


