Ousmane Amadou Dia

Ousmane Amadou Dia, Theofanis Karaletsos, Caner Hazirbas et al.

The susceptibility of deep learning models to adversarial perturbations has stirred renewed attention in adversarial examples resulting in a number of attacks. However, most of these attacks fail to encompass a large spectrum of adversarial perturbations that are imperceptible to humans. In this paper, we present localized uncertainty attacks, a novel class of threat models against deterministic and stochastic classifiers. Under this threat model, we create adversarial examples by perturbing only regions in the inputs where a classifier is uncertain. To find such regions, we utilize the predictive uncertainty of the classifier when the classifier is stochastic or, we learn a surrogate model to amortize the uncertainty when it is deterministic. Unlike $\ell_p$ ball or functional attacks which perturb inputs indiscriminately, our targeted changes can be less perceptible. When considered under our threat model, these attacks still produce strong adversarial examples; with the examples retaining a greater degree of similarity with the inputs.

Ousmane Amadou Dia, Elnaz Barshan, Reza Babanezhad

While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving adversarial examples. First, we present a manifold learning method to capture the semantics of the inputs. The motivating principle is to learn the low-dimensional geometric summaries of the inputs via statistical inference. Then, we perturb the elements of the learned manifold using the Gram-Schmidt process to induce the perturbed elements to remain in the manifold. To produce adversarial examples, we propose an efficient algorithm whereby we leverage the semantics of the inputs as a source of knowledge upon which we impose adversarial constraints. We apply our approach on toy data, images and text, and show its effectiveness in producing semantics preserving adversarial examples which evade existing defenses against adversarial attacks.