扩展不可学习的例子 使用高性能计算学习
Yanfan Zhu1, Issac Lyngaas2, Murali Gopalakrishnan Meena2
1Vanderbilt University, Nashville, TN, USA.
概括
无法学习的例子 (UE) 通过使人工智能模型无法学习敏感信息来增强数据安全性. 最佳批量大小对于深度学习中有效的UE性能至关重要,因数据集而异.
科学领域:
- 人工智能的人工智能
- 数据安全 数据安全
- 机器学习 机器学习
背景情况:
- 像ChatGPT这样的AI模型可能无意中保留敏感的医疗保健数据.
- 在人工智能诊断中使用的医学成像数据带来隐私和知识产权风险.
- 无法学习的例子 (UE) 提供了一种新的方法,以防止深度学习模型学习特定数据.
研究的目的:
- 使用高性能计算 (HPC) 来扩展不可学习的集群 (UC) 以提高UE性能.
- 调查批量大小对HPC级别的UE疗效的影响.
- 增强数据安全,防止人工智能模型中的未经授权的学习.
主要方法:
- 在峰会超级计算机上使用分布式数据并行 (DDP) 培训.
- 在各种数据集 (Pets,MedMNist,Flowers,Flowers102) 上进行实验.
- 在不同的数据集中分析了批量大小和不可学习性之间的关系.
主要成果:
- 在HPC上扩展UC使得使用大批次尺寸探索UE性能成为可能.
- 过大和过小的批量大小都会对UE的性能和准确性产生负面影响.
- 不易学习的最佳批量大小在数据集之间有很大的差异.
结论:
- 选择适当的批量大小对于使用UE的有效数据保护至关重要.
- 特定于数据集的批量大小策略是必要的,以实现最佳的不可学习性.
- 高性能计算和DDP框架促进了强大的UE研究,以提高AI数据安全性.
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
Machines: Problem Solving II
626
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
626
Introduction to Learning
903
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
903
Parallel Processing
605
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
605
Improving Translational Accuracy
3.5K
3.5K
Improving Translational Accuracy
14.0K
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...
14.0K

