论文标题
迈向理论上对变异自动编码器的鲁棒性的理解
Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
论文作者
论文摘要
我们进一步了解变异自动编码器（VAE）对对抗性攻击和其他输入扰动的鲁棒性。尽管以前的工作已经开发了攻击和捍卫VAE的算法方法，但对于VAE的强大含义仍然缺乏形式化。为了解决这个问题，我们在概率模型中开发了一个新颖的鲁棒性标准：$ r $ bobustness。然后，我们使用它来构建VAE鲁棒性的第一个理论结果，从而在输入空间中得出了边距，我们可以为此提供有关结果重建的保证。非正式地，我们能够定义一个区域，在该区域中，任何扰动都会产生与原始重建相似的重建。为了支持我们的分析，我们表明，使用解开方法训练的VAE不仅在我们的稳健性指标下得分很好，而且可以通过我们的理论结果来解释这一点的原因。
We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations. While previous work has developed algorithmic approaches to attacking and defending VAEs, there remains a lack of formalization for what it means for a VAE to be robust. To address this, we develop a novel criterion for robustness in probabilistic models: $r$-robustness. We then use this to construct the first theoretical results for the robustness of VAEs, deriving margins in the input space for which we can provide guarantees about the resulting reconstruction. Informally, we are able to define a region within which any perturbation will produce a reconstruction that is similar to the original reconstruction. To support our analysis, we show that VAEs trained using disentangling methods not only score well under our robustness metrics, but that the reasons for this can be interpreted through our theoretical results.
