不同私有贝叶斯神经网络在准确性,隐私性和可靠性方面
Qiyiwen Zhang1, Zhiqi Bu1, Kan Chen1
1University of Pennsylvania.
概括
我们为贝叶斯神经网络 (BNNs) 引入差异隐私,以量化预测不确定性. 我们的DP-BNNs提供了一个新的隐私可靠性权衡,DP-SGLD在强大的隐私保证下显示出强大的准确性.
科学领域:
- 机器学习 机器学习
- 人工智能的人工智能
- 网络安全 网络安全
背景情况:
- 常规神经网络缺乏不确定性量化,这是贝叶斯神经网络 (BNN) 的一个关键优势.
- 与差异隐私 (DP) 集成的BNNs在很大程度上未被探索,限制了隐私意识的不确定性量化.
- 现有的DP方法经常面临隐私保证和预测准确性之间的直接权衡.
研究的目的:
- 通过开发DP-BNNs来弥合贝叶斯深度学习和差异隐私之间的差距.
- 在DP框架内精确分析BNN的隐私准确性权衡.
- 引入新的DP-BNN方法来量化不确定性,并评估其性能.
主要方法:
- 提出了三个不同的DP-BNN方法:DP-SGLD (噪声梯度),DP-BBP (参数扰动) 和DP-MC Dropout (架构修改).
- 利用贝叶斯深度学习和隐私会计的最新进展进行精确的分析.
- 进行了广泛的实验,将DP-BNNs与非DP和非贝叶斯方法进行比较.
主要成果:
- 证明DP-SGD和DP-SGLD之间的等价性,表明一些非贝叶斯DP培训中的固有不确定性量化.
- 在DP-SGD和DP-SGLD之间确定了不同的超参数效应 (学习率,批量大小).
- 观察到一个新的隐私可靠性权衡;DP-SGLD在强有力的隐私保证下实现了显著的准确性.
结论:
- DP-BNNs成功地将不确定性量化与差异隐私相结合.
- DP-SGLD是一个有前途的方法,提供高精度,同时保持强大的隐私.
- 对于需要隐私和可靠预测的现实应用程序,DP-BNNs具有显著的潜力.
相关概念视频
Accuracy, limits, and approximation
475
Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
475
Neural Regulation
39.5K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
39.5K
Accuracy and Precision
8.9K
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. Highly accurate...
8.9K
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
96
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
96
Neural Circuits
1.3K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.3K
Sensitivity, Specificity, and Predicted Value
488
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
488


