用户孤立毒害在去中心化联合学习:一个敌对的消息传递图形神经网络方法
IEEE transactions on neural networks and learning systems
|December 2, 2025
概括
一个新的网络攻击,用户隔离中毒 (UIP),通过隔离良性模型更新来准去中心化联合学习 (DFL). 这种攻击显著降低了DFL的准确性,并规避了当前的防御.
科学领域:
- 网络安全 网络安全
- 机器学习 机器学习
- 分散式系统 分散式系统 分散式系统
背景情况:
- 分散的联合学习 (DFL) 允许在不集中数据的情况下进行协作模型培训.
- 确保DFL对恶意参与者的完整性和安全性是一个关键的挑战.
研究的目的:
- 引入一种新的网络攻击,用户隔离毒害 (UIP),旨在破坏DFL.
- 证明UIP在降低DFL模型精度方面的有效性.
主要方法:
- 一个恶意用户在DFL协议中策略性地制作和分发受损的模型更新.
- 一个对抗性消息传递图 (MPG) 神经网络被用来通过改进它们的表示来隔离良性模型更新.
- 在MPG内部有针对性的功能交换操纵良性模型更新,减少其影响.
主要成果:
- 拟议的用户隔离中毒攻击有效地将DFL的测试准确性降低了49.5%.
- 基于MPG的UIP攻击成功地绕过了基于共弦相似度和欧几里德距离的现有防御策略.
结论:
- 用户孤立毒害对分散的联合学习的完整性构成重大威胁.
- 需要新的防御机制来应对像UIP这样操纵模型更新的先进攻击.
相关概念视频
Neuromuscular Junction And Blockade
4.7K
The site of chemical communication between a motor neuron and a muscle fiber is called the neuromuscular junction (NMJ). The end of the motor neuron at the NMJ divides into a cluster of synaptic end bulbs. The cytoplasm of these bulbs consists of synaptic vesicles enclosing acetylcholine molecules, the principal neurotransmitter released at the NMJ. The region opposite the synaptic bulb that ends in the muscle fiber is called the motor end plate, which has acetylcholine receptors. Within the...
4.7K
Masking and Demasking Agents
3.4K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
3.4K
Avoidance Learning and Learned Helplessness
2.5K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.5K
