arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2602.09182cs.CRcs.LG
收藏

一个 RNG 统治所有:随机性如何成为机器学习中的攻击向量

One RNG to Rule Them All: How Randomness Becomes an Attack Vector in Machine Learning

Elmore Family School of Electrical and Computer Engineering(电子与计算机工程系)

Kotekar Annapoorna Prabhu, Andrew Gan, Zahra Ghodsi

AI总结:

RNGGuard 通过静态分析和运行时安全执行,为机器学习系统提供随机性安全保护。

摘要:

机器学习依赖随机性作为数据采样、数据增强、权重初始化和优化等步骤中的基本组件。大多数机器学习框架使用伪随机数生成器作为随机性的来源。然而,不同框架之间在设计选择和实现上的差异、软件依赖性和硬件后端的差异,以及缺乏统计验证,可能导致之前未被探索的机器学习系统攻击向量。对随机性源的攻击可以非常隐蔽,并在现实系统中历史上已被利用。在本工作中,我们从对抗的角度审视随机性在机器学习开发流水线中的作用,并分析主要机器学习框架中 PRNG 的实现。我们提出了 RNGGuard,以帮助机器学习工程师以最小的努力来保护系统。RNGGuard 静态分析目标库的源代码,并识别出使用随机函数和模块的实例。在运行时,RNGGuard 通过将不安全的函数调用替换为符合安全规范的 RNGGuard 实现,强制安全执行随机函数。我们的评估表明,RNGGuard 提供了一种实用的方法,以弥补机器学习系统中随机性源安全性的现有差距。

英文摘要:

Machine learning relies on randomness as a fundamental component in various steps such as data sampling, data augmentation, weight initialization, and optimization. Most machine learning frameworks use pseudorandom number generators as the source of randomness. However, variations in design choices and implementations across different frameworks, software dependencies, and hardware backends along with the lack of statistical validation can lead to previously unexplored attack vectors on machine learning systems. Such attacks on randomness sources can be extremely covert, and have a history of exploitation in real-world systems. In this work, we examine the role of randomness in the machine learning development pipeline from an adversarial point of view, and analyze the implementations of PRNGs in major machine learning frameworks. We present RNGGuard to help machine learning engineers secure their systems with low effort. RNGGuard statically analyzes a target library's source code and identifies instances of random functions and modules that use them. At runtime, RNGGuard enforces secure execution of random functions by replacing insecure function calls with RNGGuard's implementations that meet security specifications. Our evaluations show that RNGGuard presents a practical approach to close existing gaps in securing randomness sources in machine learning systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑