DeepAI AI Chat
Log In Sign Up

Generate (non-software) Bugs to Fool Classifiers

by   Hiromu Yakura, et al.
University of Tsukuba

In adversarial attacks intended to confound deep learning models, most studies have focused on limiting the magnitude of the modification so that humans do not notice the attack. On the other hand, during an attack against autonomous cars, for example, most drivers would not find it strange if a small insect image were placed on a stop sign, or they may overlook it. In this paper, we present a systematic approach to generate natural adversarial examples against classification models by employing such natural-appearing perturbations that imitate a certain object or signal. We first show the feasibility of this approach in an attack against an image classifier by employing generative adversarial networks that produce image patches that have the appearance of a natural object to fool the target model. We also introduce an algorithm to optimize placement of the perturbation in accordance with the input image, which makes the generation of adversarial examples fast and likely to succeed. Moreover, we experimentally show that the proposed approach can be extended to the audio domain, for example, to generate perturbations that sound like the chirping of birds to fool a speech classifier.


page 1

page 2

page 3

page 4

page 5

page 6

page 8

page 9


Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates

To deflect adversarial attacks, a range of "certified" classifiers have ...

Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers

Deep neural networks have been shown to exhibit an intriguing vulnerabil...

Perturbations are not Enough: Generating Adversarial Examples with Spatial Distortions

Deep neural network image classifiers are reported to be susceptible to ...

GAP++: Learning to generate target-conditioned adversarial examples

Adversarial examples are perturbed inputs which can cause a serious thre...

On Trace of PGD-Like Adversarial Attacks

Adversarial attacks pose safety and security concerns for deep learning ...

A study of the effect of JPG compression on adversarial images

Neural network image classifiers are known to be vulnerable to adversari...

Adaptive Gradient Refinement for Adversarial Perturbation Generation

Deep Neural Networks have achieved remarkable success in computer vision...

Code Repositories


Generate (non-software) Bugs to Fool Classifiers

view repo