Ross and Doshi-Velez propose input gradient regularization to improve robustness and interpretability of neural networks. As the discussion of interpretability is quite limited in the paper, the main contribution is an extensive evaluation of input gradient regularization against adversarial examples – in comparison to defenses such as distillation or adversarial training. Specifically, input regularization as proposed in [1] is used:

$\arg\min_\theta H(y,\hat{y}) + \lambda \|\nabla_x H(y,\hat{y})\|_2^2$

where $\theta$ are the network’s parameters, $x$ its input and $\hat{y}$ the predicted output. Here, $H$ might be a cross-entropy loss. It also becomes apparent why this regularization was originally called double-backpropagation because the second derivative is necessary during training.
In experiments, the authors show that the proposed regularization is superior to many other defenses including distillation and adversarial training. Unfortunately, the comparison does not include other “regularization” techniques to improve robustness – such as Lipschitz regularization. This makes the comparison less interpretable, especially as the combination of input gradient regularization and adversarial training performs best (suggesting that adversarial training is a meaningful defense, as well). Still, I recommend a closer look on the experiments. For example, the authors also study the input gradients of defended models, leading to some interesting conclusions.

[1] H. Drucket, Y. LeCun. Improving generalization performance using double backpropagation. IEEE Transactions on Neural Networks, 1992.

Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).

Hein and Andriushchenko give a intuitive bound on the robustness of neural networks based on the local Lipschitz constant. With robustness, the authors refer a small $\epsilon$-ball around each sample; this ball is supposed to describe the region where the neural network predicts a constant class. This means that adversarial examples have to compute changes large enough to leave these robust areas. Larger $\epsilon$-balls imply higher robustness to adversarial examples.

When considering a single example $x$, and a classifier $f = (f_1, \ldots, f_K)^T$ (i.e. in a multi-class setting), the bound can be stated as follows. For $q$ and $p$ such that $\frac{1}{q} + \frac{1}{p} = 1$ and $c$ being the class predicted for $x$, the it holds

$x = \arg\max_j f_j(x + \delta)$

for all $\delta$ with

$\|\delta\|_p \leq \max_{R > 0}\min \left\{\min_{j \neq c} \frac{f_c(x) – f_j(x)}{\max_{y \in B_p(x, R)} \|\nabla f_c(y) - \nabla f_j(y)\|_q}, R\right\}$.

Here, $B_p(x, R)$ describes the $R$-ball around $x$ measured using the $p$-norm. Based on the local Lipschitz constant (in the denominator), the bound essentially measures how far we can deviate from the sample $x$ (measured in the $p$-norm) until $f_j(x) > f_c(x)$ for some $j \neq c$. The higher the local Lipschitz constant, the smaller deviations are allowed, i.e. adversarial examples are easier to find. Note that the bound also depends on the confidence, i.e. the edge  $f_c(x)$ has in comparison to all other $f_j(x)$.

In the remaining paper, the authors also provide bounds for simple classifiers including linear classifiers, kernel methods and two-layer perceptrons (i.e. one hidden layer). For the latter, they also propose a new type of regularization called cross-Lipschitz regularization:

$P(f) = \frac{1}{nK^2} \sum_{i = 1}^n \sum_{l,m = 1}^K \|\nabla f_l(x_i) - \nabla f_m(x_i)\|_2^2$.

This regularization term is intended to reduce the Lipschitz constant locally around training examples. They show experimental results using this regularization on MNIST and CIFAR, see the paper for details.

Also view this summary at [davidstutz.de](https://davidstutz.de/category/reading/).

Simon-Gabriel et al. Study the robustness of neural networks with respect to the input dimensionality. Their main hypothesis is that the vulnerability of neural networks against adversarial perturbations increases with the input dimensionality. To support this hypothesis, they provide a theoretical analysis as well as experiments.

The general idea of robustness is that small perturbations $\delta$ of the input $x$ do only result in small variations $\delta \mathcal{L}$ of the loss:

$\delta \mathcal{L} = \max_{\|\delta\| \leq \epsilon} |\mathcal{L}(x + \delta) - \mathcal{L}(x)| \approx \max_{\|\delta\| \leq \epsilon} |\partial_x \mathcal{L} \cdot \delta| = \epsilon \||\partial_x \mathcal{L}\||$

where the approximation is due to a first-order Taylor expansion and $\||\cdot\||$ is the dual norm of $\|\cdot\|$. As a result, the vulnerability of networks can be quantified by considering $\epsilon\mathbb{E}_x\||\partial_x \mathcal{L}\||$. A natural regularizer to increase robustness (i.e. decrease vulnerability) would be $\epsilon \||\partial_x \mathcal{L}\||$ which is a similar regularizer as proposed in [1].

The remainder of the paper studies the norm $\|\partial_x \mathcal{L}\|$ with respect to the input dimension $d$. Specifically, they show that the gradient norm increases monotonically with the input dimension. I refer to the paper for the exact theorems and proofs. This claim is based on the assumption of non-trained networks that have merely been initialized. However, in experiments, they show that the conclusion may hold true in realistic settings, e.g. on ImageNet.

[1] Matthias Hein, Maksym Andriushchenko:
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation. NIPS 2017: 2263-2273

Also view this summary at [davidstutz.de](https://davidstutz.de/category/reading/).

Nayebi and Ganguli propose saturating neural networks as defense against adversarial examples. The main observation driving this paper can be stated as follows: Neural networks are essentially based on linear sums of neurons (e.g. fully connected layers, convolutiona layers) which are then activated; by injecting a small amount of noise per neuron it is possible to shift the final sum by large values, thereby propagating the noisy through the network and fooling the network into misclassifying an example. To prevent the impact of these adversarial examples, the network should be trained in a manner to drive many neurons into a saturated regime – noisy will, so the argument, have less impact then. The authors also give a biological motivation, which I won't go into detail here.

Letting $\psi$ be the used activation function, e.g. sigmoid or ReLU, a regularizer is added to drive neurons into saturation. In particular, a penalty
$\lambda \sum_l \sum_i \psi_c(h_i^l)$
is added to the loss. Here, $l$ indexes the layer and $i$ the unit in the layer; $h_i^l$ then describes the input to the non-linearity computed for unit $i$ in layer $l$. $\psi_c$ is the complementary function defined as
$\psi_c(z) = \inf_{z': \psi'(z') = 0} |z – z'|$
It defines the distance of the point $z$ to the nearest saturated point $z'$ where $\psi'(z') = 0$. For ReLU activations, the complementary function is the ReLU function itself; for sigmoid activations, the complementary function is
$\sigma_c(z) = |\sigma(z)(1 - \sigma(z))|$.
In experiments, Nayebi and Ganguli show that training with the additional penalty yields networks with higher robustness against adversarial examples compared to adversarial training (i.e. training on adversarial examples). They also provide some insight, showing e.g. the activation and weight distribution of layers illustrating that neurons are indeed saturated in large parts. For details, see the paper.

I also want to point to a comment on the paper written by Brendel and Bethge [1] questioning the effectiveness of the proposed defense strategy. They discuss a variant of the fast sign gradient method (FSGM) with stabilized gradients which is able to fool saturated networks.

[1] W. Brendel, M. Behtge. Comment on “Biologically inspired protection of deep networks from adversarial attacks”, https://arxiv.org/abs/1704.01547.

Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).

Xu et al. propose feature squeezing for detecting and defending against adversarial examples. In particular, they consider “squeezing” the bit depth of the input images as well as local and non-local smoothing (Gaussian, median filtering etc.). In experiments they show that feature squeezing preserves accuracy while defending against adversarial examples. Figure 1 additionally shows an illustration of how feature squeezing can be used to detect adversarial examples.

https://i.imgur.com/Ixv522J.png
Figure 1: Illustration of using squeezing for adversarial example detection.

Also find this summary on [davidstutz.de](https://davidstutz.de/category/reading/).