论文标题
首先猜测以实现更好的压缩和对抗性鲁棒性
Guess First to Enable Better Compression and Adversarial Robustness
论文作者
论文摘要
机器学习模型通常容易受到对抗性例子的影响，这与人类的鲁棒性形成鲜明对比。在本文中，我们试图利用人类识别中的一种机制，并提出了一个受生物启发的分类框架，其中模型推断是在标签假设上进行的。我们为此框架提供一类培训目标，并提供信息瓶颈正常化程序，该程序利用了可以在推断过程中丢弃标签信息的优势。该框架可以更好地压缩输入和潜在表示之间的共同信息，而不会损失学习能力，而以可拖动的推理复杂性为代价。更好的压缩和消除标签信息进一步带来了更好的对抗性鲁棒性，而不会丧失自然精度，这在实验中得到了证明。
Machine learning models are generally vulnerable to adversarial examples, which is in contrast to the robustness of humans. In this paper, we try to leverage one of the mechanisms in human recognition and propose a bio-inspired classification framework in which model inference is conditioned on label hypothesis. We provide a class of training objectives for this framework and an information bottleneck regularizer which utilizes the advantage that label information can be discarded during inference. This framework enables better compression of the mutual information between inputs and latent representations without loss of learning capacity, at the cost of tractable inference complexity. Better compression and elimination of label information further bring better adversarial robustness without loss of natural accuracy, which is demonstrated in the experiment.
