1 code implementation • 20 Apr 2022 • Loris Giulivi, Malhar Jere, Loris Rossi, Farinaz Koushanfar, Gabriela Ciocarlie, Briland Hitaj, Giacomo Boracchi
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.
1 code implementation • 5 Dec 2019 • Malhar Jere, Loris Rossi, Briland Hitaj, Gabriela Ciocarlie, Giacomo Boracchi, Farinaz Koushanfar
We study black-box adversarial attacks for image classifiers in a constrained threat model, where adversaries can only modify a small fraction of pixels in the form of scratches on an image.