强大的联合学习:对抗拜占庭袭击的最大对流聚合
IEEE transactions on neural networks and learning systems
|April 23, 2024
概括
联合学习面临来自不可靠设备的挑战. 最大流聚合 (MCA) 通过使用一种新的相似度指标来安全聚合参数,增强模型完整性,提供了强大的防御.
科学领域:
- 分散式机器学习 (Machine Learning) 是一种分散式的机器学习.
- 人工智能中的网络安全
背景情况:
- 联合学习使协作培训成为可能,同时保持参与者的隐私和安全.
- 不值得信赖的设备,如拜占庭攻击者,可以通过上传恶意参数来破坏联合学习,破坏全球模型.
研究的目的:
- 提出一种新的强大的聚合方法,即最大电流聚合 (MCA),以保护联合学习免受恶意参数上传.
- 使用最大电流标准 (MCC) 作为强大的参数聚合的相似度指标,与其以前在无声化中的使用不同.
主要方法:
- 开发了MCA,应用MCC通过测量参数分布相似性来从参数中推导中心值.
- 采用固定点代来解决优化目标,证明线性收.
- 进行理论分析以确定MCA的稳定性聚合属性和错误极限.
主要成果:
- MCA有效地使用电流测量参数分布,捕获高阶统计属性以抵御攻击者.
- 该方法不需要了解恶意攻击者的比例.
- 在三个数据集中对IID和非IID数据的实验结果表明MCA对主流攻击具有显著的稳定性.
结论:
- MCA为联合学习提供了强大的聚合方法,有效地减轻了恶意参与者的影响.
- 拟议的技术提供了对拜占庭袭击的强有力的防御,在弹性方面超过了现有的方法.
相关概念视频
Associative Learning
345
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...
345
Propagation of Uncertainty from Random Error
681
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...
681
Aggregates Classification
317
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
317
Maximum Size of Aggregate
112
The maximum size of aggregate is defined as the aperture of the sieve retaining 15 percent or more of the particles present in the aggregate sample. The aggregate's maximum size impacts the concrete's water requirement, workability, and strength. Larger aggregates reduce the surface area needing cement paste coverage, which can lower water needs, thereby allowing a decrease in the water-to-cement ratio when the desired workability and richness of the mix are to be maintained, which can...
112
Propagation of Uncertainty from Systematic Error
517
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...
517
Multimachine Stability
151
Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
151


