马特里奥什卡:利用深度学习模型的过度参数化来进行秘密数据传输
概括
一种新的内部攻击,Matryoshka,可以从没有接口的私有机器学习 (ML) 模型中窃取数据. 这种攻击将秘密模型隐藏在运营商模型中,从而保护数据隐私和模型实用性.
科学领域:
- 机器学习安全 机器学习安全
- 数据 隐私 数据 隐私 数据
- 网络安全 网络安全
背景情况:
- 高质量的私有机器学习 (ML) 数据对于人工智能的竞争力至关重要.
- 在本地数据中心保护敏感的ML数据是一个重大挑战.
研究的目的:
- 引入一种新的内部攻击,Matryoshka,这违反了ML数据隐私.
- 为了证明即使没有暴露的接口,也可以提取私有ML数据的可能性.
主要方法:
- 采用预定发布的深度神经网络 (DNN) 作为秘密数据传输的载体模型.
- 使用一种新的参数共享方法来利用载体模型的学习能力来隐藏信息.
主要成果:
- 马特里奥什卡实现了高数据传输能力,运载机模型效用损失最小.
- 该攻击允许有效解码隐藏模型和有效恢复ML模型或原始训练数据.
- 该方法证明了对后处理和隐蔽的稳定性,使其难以检测.
结论:
- 马特里奥什卡对存储在本地数据中心的ML数据的隐私构成重大威胁.
- 攻击突出了当前ML数据安全实践中的漏洞,即使没有外部接口.
相关概念视频
Improving Translational Accuracy
9.7K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.7K
Censoring Survival Data
74
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...
74
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
66
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...
66
Reducing Line Loss
150
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
150
Multi-input and Multi-variable systems
105
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...
105
Propagation of Uncertainty from Random Error
661
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...
661


