深度学习与数据隐私通过残留扰乱.
IEEE transactions on pattern analysis and machine intelligence
|November 26, 2025
概括
我们介绍了一种新的隐私保护深度学习 (DL) 方法,使用随机微分方程. 这种方法增强了数据隐私和模型实用性,优于现有的差异性私有随机梯度下降 (DPSGD) 方法.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 数据 隐私 数据 隐私 数据
背景情况:
- 深度学习 (DL) 模型需要强大的数据隐私措施.
- 现有的保护隐私的DL方法往往会损害效用,增加计算成本.
- 差异隐私 (DP) 是保证隐私的关键标准.
研究的目的:
- 为保护隐私的深度学习提出一种新的,计算效率高的方法.
- 从理论和经验上验证拟议方法在维护数据隐私和模型实用性的有效性.
- 将拟议的方法与最先进的差异性私人方法进行比较.
主要方法:
- 引入了一种新的基于随机微分方程的残余扰动技术.
- 高斯噪声被注入到ResNets的剩余映射中,以保护隐私.
- 理论分析证明差异隐私 (DP) 和减少泛化差距.
- 经验评估与差异性私人随机梯度下降 (DPSGD) 的比较.
主要成果:
- 拟议的残余扰动方法保证了差异隐私 (DP).
- 该方法被证明可以减少深度学习模型中的概括差距.
- 剩余扰动证明了计算效率.
- 与最先进的DPSGD相比,实证上优越的公用事业维护,而不会牺牲会员隐私.
结论:
- 基于静态微分方程的残余扰动为保护隐私的深度学习提供了有效的解决方案.
- 这种方法平衡了强大的隐私保证与高模型实用性和计算效率.
- 它代表了与现有的差异性私人培训方法 (如DPSGD) 相比的重大进步.
相关概念视频
Survival Tree
374
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...
374
Residual Plots
6.0K
A residual plot is a statistical representation of data used to analyze correlation and regression results. It helps verify the requirements for drawing specific conclusions about correlation and regression. To obtain the residual plot, first, the residual for each data value is calculated, which is simply the vertical distance between the observed and the predicted value obtained from the regression equation.
When the residual values are plotted against the variable x, it is called a residual...
When the residual values are plotted against the variable x, it is called a residual...
6.0K
Residuals and Least-Squares Property
8.9K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
8.9K
Censoring Survival Data
507
Survival analysis is a statistical method used to analyze time-to-event data, often employed in fields such as medicine, engineering, and social sciences. One of the key challenges in survival analysis is dealing with incomplete data, a phenomenon known as "censoring." Censoring occurs when the event of interest (such as death, relapse, or system failure) has not occurred for some individuals by the end of the study period or is otherwise unobservable, and it might have many different...
507
Propagation of Uncertainty from Random Error
1.6K
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...
1.6K
