arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.02883cs.LGcs.CR
收藏

针对不可学习数据集的非线性变换

Nonlinear Transformations Against Unlearnable Datasets

University of South Florida(佛罗里达州立大学);Fordham University(福特汉姆大学)

Thushari Hapuarachchi, Jing Lin, Kaiqi Xiong, Mohamed Rahouti, Gitte Ost

AI总结:

研究提出一种非线性变换框架,通过实验证明深度神经网络能从十二种方法生成的“不可学习”数据中有效学习,相比线性可分技术提升0.34%至249.59%的测试准确率,揭示现有数据保护方法不足。

摘要:

自动化爬取是深度学习模型中未经数据所有者授权收集数据的常见方法。近期研究开始解决这种数据收集方法带来的隐私问题。显著的方法包括Deepconfuse、误差最小化、误差最大化(也称为对抗性投毒)、神经正切泛化攻击、合成、自回归、单像素捷径、自集成保护、纠缠特征、鲁棒误差最小化、虚伪和TensorClog。这些方法生成的数据称为“不可学习”样本,阻止深度学习模型“学习”。在本研究中,我们调查并设计了一个有效的非线性变换框架,并进行大量实验,证明深度神经网络能够有效从上述十二种方法产生的传统上被认为不可学习的数据/样本中学习。与研究人员最近提出的线性可分技术相比,所提出的方法提高了破解不可学习数据的能力。具体来说,我们的大量实验表明,对于这些十二种数据保护方法生成的不可学习CIFAR10数据集(除单像素捷径外),改进范围为0.34%至249.59%。此外,与线性可分技术相比,所提出的框架在自回归和REM方法上实现了超过100%的测试准确率提升。我们的发现表明,这些方法不足以防止机器学习模型中数据的未经授权使用。迫切需要开发更强大的保护机制,有效阻止攻击者在未经所有者适当授权的情况下访问数据。

英文摘要:

Automated scraping stands out as a common method for collecting data in deep learning models without the authorization of data owners. Recent studies have begun to tackle the privacy concerns associated with this data collection method. Notable approaches include Deepconfuse, error-minimizing, error-maximizing (also known as adversarial poisoning), Neural Tangent Generalization Attack, synthetic, autoregressive, One-Pixel Shortcut, Self-Ensemble Protection, Entangled Features, Robust Error-Minimizing, Hypocritical, and TensorClog. The data generated by those approaches, called "unlearnable" examples, are prevented "learning" by deep learning models. In this research, we investigate and devise an effective nonlinear transformation framework and conduct extensive experiments to demonstrate that a deep neural network can effectively learn from the data/examples traditionally considered unlearnable produced by the above twelve approaches. The resulting approach improves the ability to break unlearnable data compared to the linear separable technique recently proposed by researchers. Specifically, our extensive experiments show that the improvement ranges from 0.34% to 249.59% for the unlearnable CIFAR10 datasets generated by those twelve data protection approaches, except for One-Pixel Shortcut. Moreover, the proposed framework achieves over 100% improvement of test accuracy for Autoregressive and REM approaches compared to the linear separable technique. Our findings suggest that these approaches are inadequate in preventing unauthorized uses of data in machine learning models. There is an urgent need to develop more robust protection mechanisms that effectively thwart an attacker from accessing data without proper authorization from the owners.

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。

↑