2022-04-21 更新
Adversarial Scratches: Deployable Attacks to CNN Classifiers
Authors:Loris Giulivi, Malhar Jere, Loris Rossi, Farinaz Koushanfar, Gabriela Ciocarlie, Briland Hitaj, Giacomo Boracchi
A growing body of work has shown that deep neural networks are susceptible to adversarial examples. These take the form of small perturbations applied to the model’s input which lead to incorrect predictions. Unfortunately, most literature focuses on visually imperceivable perturbations to be applied to digital images that often are, by design, impossible to be deployed to physical targets. We present Adversarial Scratches: a novel L0 black-box attack, which takes the form of scratches in images, and which possesses much greater deployability than other state-of-the-art attacks. Adversarial Scratches leverage B\’ezier Curves to reduce the dimension of the search space and possibly constrain the attack to a specific location. We test Adversarial Scratches in several scenarios, including a publicly available API and images of traffic signs. Results show that, often, our attack achieves higher fooling rate than other deployable state-of-the-art methods, while requiring significantly fewer queries and modifying very few pixels.
PDF This paper stems from ‘Scratch that! An Evolution-based Adversarial Attack against Neural Networks’ for which an arXiv preprint is available at arXiv:1912.02316. Further studies led to a complete overhaul of the work, resulting in this paper. This work was submitted for review in Pattern Recognition (Elsevier)
论文截图
