IAM

Check out our latest research on adversarial robustness and generalization of deep networks.
06thMAY2018

READING

Nina Narodytska, Shiva Prasad Kasiviswanathan. Simple Black-Box Adversarial Attacks on Deep Neural Networks. CVPR Workshops 2017.

Narodytska and Kasiviswanathan propose a local search-based black.box adversarial attack against deep networks. In particular, they address the problem of k-misclassification defined as follows:

Definition (k-msiclassification). A neural network k-misclassifies an image if the true label is not among the k likeliest labels.

To this end, they propose a local search algorithm which, in each round, randomly perturbs individual pixels in a local search area around the last perturbation. If a perturbed image satisfies the k-misclassificaiton condition, it is returned as adversarial perturbation. While the approach is very simple, it is applicable to black-box models where gradients and or internal representations are not accessible but only the final score/probability is available. Still the approach seems to be quite inefficient, taking up to one or more seconds to generate an adversarial example. Unfortunately, the authors do not discuss qualitative results and do not give examples of multiple adversarial examples (except for the four in Figure 1).

Figure 1: Examples of adversarial attacks. Top: original image, bottom: perturbed image.

Also find this summary on ShortScience.org.

What is your opinion on the summarized work? Or do you know related work that is of interest? Let me know your thoughts in the comments below or get in touch with me: