Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack methods make unrealistic assumptions, assuming that all training data comes from a single source and that attackers have full access to the training data. In this paper, we introduce a more realistic attack scenario where victims collect data from multiple sources, and attackers cannot access the complete training data. We refer to this scenario as data-constrained backdoor attacks. In such cases, previous attack methods suffer from severe efficiency degradation due to the entanglement between benign and poisoning features during the backdoor injection process. To tackle this problem, we introduce three CLIP-based technologies from two distinct streams: Clean Feature Suppression and Poisoning Feature Augmentation.effective solution for data-constrained backdoor attacks. The results demonstrate remarkable improvements, with some settings achieving over 100% improvement compared to existing attacks in data-constrained scenarios. Code is available at https://github.com/sunh1113/Efficient-backdoor-attacks-for-deep-neural-networks-in-real-world-scenarios

翻译：近期深度神经网络（DNNs）高度依赖于海量训练数据，这为恶意攻击者提供了利用并污染数据实施后门攻击的机会。然而，现有后门攻击方法存在不切实际的假设，即假定所有训练数据均来自单一来源且攻击者能完全访问训练数据。本文引入了一种更贴合实际的攻击场景：受害者从多个数据源收集数据，而攻击者无法获取完整的训练数据。我们将此场景称为数据受限的后门攻击。在此类场景下，由于后门注入过程中良性特征与中毒特征相互纠缠，现有攻击方法的效率严重下降。为解决该问题，我们提出了三种基于CLIP的技术，分别归属于两个不同方向：干净特征抑制与中毒特征增强，从而为数据受限的后门攻击提供了有效解决方案。实验结果表明，该方法取得了显著提升，在部分设置下相较于现有数据受限场景攻击实现了超过100%的性能改进。代码开源地址：https://github.com/sunh1113/Efficient-backdoor-attacks-for-deep-neural-networks-in-real-world-scenarios