As a result of increasingly adopted machine learning algorithms and ubiquitous sensors, many 'perception-to-control' systems are developed and deployed. For these systems to be trustworthy, we need to improve their robustness with adversarial training being one approach. We propose a gradient-free adversarial training technique, called AutoJoin, which is a very simple yet effective and efficient approach to produce robust models for imaged-based maneuvering. Compared to other SOTA methods with testing on over 5M perturbed and clean images, AutoJoin achieves significant performance increases up to the 40% range under gradient-free perturbations while improving on clean performance up to 300%. Regarding efficiency, AutoJoin demonstrates strong advantages over other SOTA techniques by saving up to 83% time per training epoch and 90% training data. Although not the focus of AutoJoin, it even demonstrates superb ability in defending gradient-based attacks. The core idea of AutoJoin is to use a decoder attachment to the original regression model creating a denoising autoencoder within the architecture. This architecture allows the tasks 'maneuvering' and 'denoising sensor input' to be jointly learnt and reinforce each other's performance.
翻译:由于越来越多地采用机器学习算法和无处不在的传感器,许多“感知到控制”系统得到开发和部署。为了能够信任这些系统,我们需要提高它们的稳健性能,而对抗性培训则是一种方法。我们建议采用一个叫AutoJoin的无梯度对抗性培训技术,称为AutoJoin,这是一个非常简单、有效、高效的方法,可以产生以图像为基础的机动操作的强力模型。与其他SOTA方法相比,AutoJoin通过对5M 以上窥视和清洁图像进行测试,可以取得高达40%的无梯度扰动干扰系统下的超强性能,同时将性能改进到300 %。关于效率,AutoJoin通过节省高达83%的每次培训时间和90%的培训数据,与其他SOTA技术相比表现出巨大的优势。虽然AutoJoin没有重点,但它甚至展示了在保护基于梯度的攻击方面的超强能力。AutoJoin的核心思想是利用原始回归模型的解码附加装置,在结构内创建一个解析的自动电解码器,在结构内将自动电解析器中创建。这一结构内,使每个任务都能够学习和感官化。