Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples have a secret property, i. e., a trigger. At inference time, the secret functionality is activated when the input contains the trigger, while the model functions correctly in other cases. While there are many known backdoor attacks (and defenses), deploying a stealthy attack is still far from trivial. Successfully creating backdoor triggers depends on numerous parameters. Unfortunately, research has not yet determined which parameters contribute most to the attack performance. This paper systematically analyzes the most relevant parameters for the backdoor attacks, i.e., trigger size, position, color, and poisoning rate. Using transfer learning, which is very common in computer vision, we evaluate the attack on state-of-the-art models (ResNet, VGG, AlexNet, and GoogLeNet) and datasets (MNIST, CIFAR10, and TinyImageNet). Our attacks cover the majority of backdoor settings in research, providing concrete directions for future works. Our code is publicly available to facilitate the reproducibility of our results.
翻译:深度学习在许多机器学习任务中取得了杰出的成果。然而,它容易受到背景干扰攻击的影响,从而修改训练数据集并在训练模型中嵌入秘密功能。这些被修改的训练样本具有秘密属性,即触发器。在推理时,当输入包含触发器时,秘密功能会被激活,而在其他情况下,模型会正确运行。尽管已有许多已知的背景干扰攻击(和防御)方法,但成功创建背景干扰触发器仍然远非易事,需要考虑很多参数。不幸的是,尚未确定哪些参数对攻击性能的贡献最大。本文系统地分析了背景干扰攻击的最相关参数,如触发器大小,位置,颜色和污染率。使用计算机视觉中广泛使用的迁移学习,我们评估了现代模型(ResNet,VGG,AlexNet和GoogLeNet)和数据集(MNIST,CIFAR10和TinyImageNet)上的攻击。我们的攻击涵盖了研究中的大多数背景干扰设置,为未来的研究提供了具体的方向。我们的代码已公开发布,以便于我们的结果的可重复性。