Adversarial examples are one of the most severe threats to deep learning
models. Numerous works have been proposed to study and defend adversarial
examples. However, these works lack analysis of adversarial information or
perturbation, which cannot reveal the mystery of adversarial examples and lose
proper interpretation. In this paper, we aim to fill this gap by studying
adversarial information as unstructured noise, which does not have a clear
pattern. Specifically, we provide some empirical studies with singular value
decomposition, by decomposing images into several matrices, to analyze
adversarial information for different attacks. Based on the analysis, we
propose a new module to regularize adversarial information and combine
information bottleneck theory, which is proposed to theoretically restrict
intermediate representations. Therefore, our method is interpretable. Moreover,
the fashion of our design is a novel principle that is general and unified.
Equipped with our new module, we evaluate two popular model structures on two
mainstream datasets with various adversarial attacks. The results indicate that
the improvement in robust accuracy is significant. On the other hand, we prove
that our method is efficient with only a few additional parameters and able to
be explained under regional faithfulness analysis.

通过奇异值分解将图像分解为多个矩阵，对不同攻击的敌对信息进行分析，提出一种新的模块来规范敌对信息，并结合信息瓶颈理论实现中间表示的理论限制，从而提高模型的鲁棒性。

信息瓶颈结合奇异正则化改进模型的对抗鲁棒性

Singular Regularization with Information Bottleneck Improves Model's  Adversarial Robustness

Sequence-to-sequence (seq2seq) neural models have been actively investigated
for abstractive summarization. Nevertheless, existing neural abstractive
systems frequently generate factually incorrect summaries and are vulnerable to
adversarial information, suggesting a crucial lack of semantic understanding.
In this paper, we propose a novel semantic-aware neural abstractive
summarization model that learns to generate high quality summaries through
semantic interpretation over salient content. A novel evaluation scheme with
adversarial samples is introduced to measure how well a model identifies
off-topic information, where our model yields significantly better performance
than the popular pointer-generator summarizer. Human evaluation also confirms
that our system summaries are uniformly more informative and faithful as well
as less redundant than the seq2seq model.

本文提出了一种基于语义理解的神经生成式摘要模型，通过对显要内容的语义解释学习生成高质量摘要。同时引入一种新的对抗样本评估体制，证明该模型比流行的指针 - 生成式模型更好地识别了离题信息，并且人工评估结果表明本文模型生成的摘要更具信息量和可信度，且冗余度更低。