The information bottleneck (IB) principle has been adopted to explain deep learning in terms of information compression and prediction, which are balanced by a trade-off hyperparameter. How to optimize the IB principle for better robustness and figure out the effects of compression through the trade-off hyperparameter are two challenging problems. Previous methods attempted to optimize the IB principle by introducing random noise into learning the representation and achieved state-of-the-art performance in the nuisance information compression and semantic information extraction. However, their performance on resisting adversarial perturbations is far less impressive. To this end, we propose an adversarial information bottleneck (AIB) method without any explicit assumptions about the underlying distribution of the representations, which can be optimized effectively by solving a Min-Max optimization problem. Numerical experiments on synthetic and real-world datasets demonstrate its effectiveness on learning more invariant representations and mitigating adversarial perturbations compared to several competing IB methods. In addition, we analyse the adversarial robustness of diverse IB methods contrasting with their IB curves, and reveal that IB models with the hyperparameter $\beta$ corresponding to the knee point in the IB curve achieve the best trade-off between compression and prediction, and has best robustness against various attacks.
翻译:信息瓶颈原则(IB)已被采纳来解释信息压缩和预测方面的深层次学习,这种深层次学习由取舍的超参数加以平衡。如何优化IB原则以增进稳健性,并找出通过取舍的超参数进行压缩的效果,这是两个具有挑战性的问题。以前采用的方法试图优化IB原则,办法是在学习代表性时采用随机噪音,并实现骚扰信息压缩和语义信息提取方面的最先进性能。然而,他们在抵制对抗对抗性扰动方面的表现远不那么令人印象深刻。为此,我们提议采用对抗性信息瓶颈方法,而不对代表面的基本分布作任何明确假设,通过解决最小-负重优化问题可以有效优化。合成和现实世界数据集的量化实验表明,在学习更多变异性表述和减少对抗性扰动性影响方面,与若干竞争性IB方法相比,我们分析与IB曲线相对的各种IB方法的对抗性强性能。我们提议采用对抗性信息瓶法方法。为此,我们提议采用一种没有明确假设性的信息瓶颈方法。通过解决最小-负优化的模型模型和最强的IB对准度预测。