在数据中毒下超参数学习:通过多目标双级优化分析规范化的影响
IEEE transactions on neural networks and learning systems
|August 30, 2023
概括
机器学习 (ML) 算法面临着中毒攻击. 一种新的多目标双层优化方法可以考虑超参数的变化,从而更现实地评估ML模型对这些攻击的稳定性.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 机器学习 (ML) 算法容易受到数据中毒攻击,操纵的训练数据会降低性能.
- 现有的最佳攻击策略往往假定固定的超参数,导致过于悲观的稳定性评估.
研究的目的:
- 为ML中毒攻击开发一种新的最佳攻击配方,考虑超参数适应.
- 为了更准确地评估在最糟糕的攻击场景下ML模型的稳定性.
主要方法:
- 制定了最佳攻击作为一个多目标双级优化问题,并结合了超参数学习.
- 将新型攻击配方应用于L2和L1规范化的ML分类器.
- 评估了多个数据集的方法,包括深度神经网络 (DNN).
主要成果:
- 恒定规范化超参数值可能会对算法性能产生负面影响.
- 与以前的方法相比,拟议的方法提供了更准确的稳定性评估.
- 当超参数在可信数据上被学习时,L2和L1规范化有效地减轻了中毒攻击.
结论:
- 在攻击制定过程中学习超参数对于现实的强度评估至关重要.
- 规范化对于提高复杂模型的稳定性和稳定性至关重要,例如DNN对毒性攻击的防御.
更多相关视频
03:14Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
618
13:54A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM
Published on: August 18, 2023
4.6K
相关概念视频
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
89
Drugs administered through various routes can lead to nonlinear elimination, resulting in complex pharmacokinetic behaviors crucial to understanding efficacious drug dosing.
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
89
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
79
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
79
Survival Tree
109
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...
109
Multi-input and Multi-variable systems
128
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
In the absence...
128
Analysis of Population Pharmacokinetic Data
293
Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
293
Nonlinear Pharmacokinetics: Causes of Nonlinearity
228
Nonlinearity in drug pharmacokinetics is caused by various factors influencing how a drug is absorbed, distributed, metabolized, and excreted. Understanding these nonlinear processes is crucial for predicting drug behavior in the body and optimizing drug dosing regimens.
Nonlinear drug absorption can occur when the process is rate-limited by solubility, carrier-mediated transport systems, or saturation of the presystemic gut wall or hepatic metabolism. For instance, high doses of riboflavin...
Nonlinear drug absorption can occur when the process is rate-limited by solubility, carrier-mediated transport systems, or saturation of the presystemic gut wall or hepatic metabolism. For instance, high doses of riboflavin...
228
